cache/agreements_cache_dcbcd453e19427bcbf89a901d3f2a925.csv

scenario,scenario_source,ref_scenario,ref_source,corr_type,model_select_strategy,model_subset_size_requested,exp_n,correlation,p_value
Helm Lite,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,0,0.4447495899966607,0.1315867602811863
Helm Lite,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,1,0.3571428571428571,0.27509920634920637
Helm Lite,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,2,0.47280542884465016,0.10506382347888965
Helm Lite,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,3,0.2545875386086578,0.38281014365989596
Helm Lite,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,4,0.40006613209931935,0.17023995462900499
Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,0,0.07142857142857142,0.9048611111111111
Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,1,-0.2857142857142857,0.39875992063492066
Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,2,0.07142857142857142,0.9048611111111111
Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,3,-0.21428571428571427,0.5484126984126985
Helm Lite NarrativeQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,4,-0.3571428571428571,0.27509920634920637
Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,0,0.07142857142857142,0.9048611111111111
Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,1,-0.2857142857142857,0.39875992063492066
Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,2,0.14285714285714285,0.7195436507936508
Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,3,-0.21428571428571427,0.5484126984126985
Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,4,-0.2857142857142857,0.39875992063492066
Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,0,0.21428571428571427,0.5484126984126985
Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,1,0.0,1.0
Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,2,0.3571428571428571,0.27509920634920637
Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,3,0.0,1.0
Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,4,0.0,1.0
Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7637626158259734,0.008839740160738534
Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7857142857142856,0.005505952380952381
Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7857142857142856,0.005505952380952381
Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,3,0.5714285714285714,0.06101190476190476
Helm Lite OpenBookQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,4,0.7637626158259734,0.008839740160738534
Helm Lite MMLU,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7142857142857142,0.014136904761904762
Helm Lite MMLU,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7857142857142856,0.005505952380952381
Helm Lite MMLU,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,2,0.6428571428571428,0.03115079365079365
Helm Lite MMLU,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,3,0.5714285714285714,0.06101190476190476
Helm Lite MMLU,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,4,0.7142857142857142,0.014136904761904762
Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,0,0.21428571428571427,0.5484126984126985
Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,1,0.2857142857142857,0.39875992063492066
Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,2,0.4999999999999999,0.10868055555555556
Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,3,0.14285714285714285,0.7195436507936508
Helm Lite MathEquivalentCOT,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,4,0.3571428571428571,0.27509920634920637
Helm Lite GSM8K,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,0,0.5714285714285714,0.06101190476190476
Helm Lite GSM8K,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,1,0.8571428571428571,0.001736111111111111
Helm Lite GSM8K,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7142857142857142,0.014136904761904762
Helm Lite GSM8K,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,3,0.7857142857142856,0.005505952380952381
Helm Lite GSM8K,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,4,0.7142857142857142,0.014136904761904762
Helm Lite LegalBench,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,0,0.2857142857142857,0.39875992063492066
Helm Lite LegalBench,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,1,0.21428571428571427,0.5484126984126985
Helm Lite LegalBench,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,2,0.3571428571428571,0.27509920634920637
Helm Lite LegalBench,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,3,0.036369648372665396,0.9007802600472398
Helm Lite LegalBench,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,4,0.21428571428571427,0.5484126984126985
Helm Lite MedQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,0,0.6428571428571428,0.03115079365079365
Helm Lite MedQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,1,0.6428571428571428,0.03115079365079365
Helm Lite MedQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,2,0.4999999999999999,0.10868055555555556
Helm Lite MedQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,3,0.5714285714285714,0.06101190476190476
Helm Lite MedQA,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,4,0.6428571428571428,0.03115079365079365
Helm Lite WMT2014,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,0,0.6428571428571428,0.03115079365079365
Helm Lite WMT2014,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,1,0.3571428571428571,0.27509920634920637
Helm Lite WMT2014,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,2,0.42857142857142855,0.17886904761904762
Helm Lite WMT2014,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,3,0.3571428571428571,0.27509920634920637
Helm Lite WMT2014,helm_lite_240829.csv,aggregate,aggregate,kendall,random,8,4,0.3571428571428571,0.27509920634920637
HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,0,0.9285714285714285,0.0003968253968253968
HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,1,0.9285714285714285,0.0003968253968253968
HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,2,0.9285714285714285,0.0003968253968253968
HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,3,0.9285714285714285,0.0003968253968253968
HF OpenLLM v2,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,4,0.9285714285714285,0.0003968253968253968
HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7857142857142856,0.005505952380952381
HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7857142857142856,0.005505952380952381
HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,2,0.9999999999999998,4.96031746031746e-05
HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,3,0.7142857142857142,0.014136904761904762
HFv2 BBH,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,4,0.8571428571428571,0.001736111111111111
HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,0,0.4999999999999999,0.10868055555555556
HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,1,0.4999999999999999,0.10868055555555556
HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7857142857142856,0.005505952380952381
HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,3,0.7857142857142856,0.005505952380952381
HFv2 GPQA,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,4,0.3571428571428571,0.27509920634920637
HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,0,0.8571428571428571,0.001736111111111111
HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,1,0.4999999999999999,0.10868055555555556
HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7857142857142856,0.005505952380952381
HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,3,0.5714285714285714,0.06101190476190476
HFv2 IFEval,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,4,0.7142857142857142,0.014136904761904762
HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,0,0.9285714285714285,0.0003968253968253968
HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,1,0.9285714285714285,0.0003968253968253968
HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,2,0.9999999999999998,4.96031746031746e-05
HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,3,0.8571428571428571,0.001736111111111111
HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,4,0.8571428571428571,0.001736111111111111
HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,0,0.8571428571428571,0.001736111111111111
HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,1,0.5714285714285714,0.06101190476190476
HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7857142857142856,0.005505952380952381
HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,3,0.4999999999999999,0.10868055555555556
HFv2 Math Level 5,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,4,0.9285714285714285,0.0003968253968253968
HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7142857142857142,0.014136904761904762
HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,1,0.4999999999999999,0.10868055555555556
HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,2,0.5714285714285714,0.06101190476190476
HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,3,0.7857142857142856,0.005505952380952381
HFv2 MuSR,hf_open_llm_v2_240829.csv,aggregate,aggregate,kendall,random,8,4,0.6428571428571428,0.03115079365079365
Helm MMLU,helm_mmlu_240829.csv,aggregate,aggregate,kendall,random,8,0,0.5714285714285714,0.06101190476190476
Helm MMLU,helm_mmlu_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7142857142857142,0.014136904761904762
Helm MMLU,helm_mmlu_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7142857142857142,0.014136904761904762
Helm MMLU,helm_mmlu_240829.csv,aggregate,aggregate,kendall,random,8,3,0.7857142857142856,0.005505952380952381
Helm MMLU,helm_mmlu_240829.csv,aggregate,aggregate,kendall,random,8,4,0.7857142857142856,0.005505952380952381
LMSys Arena,chatbot_arena_240829.csv,aggregate,aggregate,kendall,random,8,0,0.9999999999999998,4.96031746031746e-05
LMSys Arena,chatbot_arena_240829.csv,aggregate,aggregate,kendall,random,8,1,0.9999999999999998,4.96031746031746e-05
LMSys Arena,chatbot_arena_240829.csv,aggregate,aggregate,kendall,random,8,2,0.9999999999999998,4.96031746031746e-05
LMSys Arena,chatbot_arena_240829.csv,aggregate,aggregate,kendall,random,8,3,0.9999999999999998,4.96031746031746e-05
LMSys Arena,chatbot_arena_240829.csv,aggregate,aggregate,kendall,random,8,4,0.9999999999999998,4.96031746031746e-05
MMLU Pro,mmlu_pro_240829.csv,aggregate,aggregate,kendall,random,8,0,0.8571428571428571,0.001736111111111111
MMLU Pro,mmlu_pro_240829.csv,aggregate,aggregate,kendall,random,8,1,0.9285714285714285,0.0003968253968253968
MMLU Pro,mmlu_pro_240829.csv,aggregate,aggregate,kendall,random,8,2,0.8571428571428571,0.001736111111111111
MMLU Pro,mmlu_pro_240829.csv,aggregate,aggregate,kendall,random,8,3,0.9285714285714285,0.0003968253968253968
MMLU Pro,mmlu_pro_240829.csv,aggregate,aggregate,kendall,random,8,4,0.9285714285714285,0.0003968253968253968
MixEval,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7857142857142856,0.005505952380952381
MixEval,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,1,0.8571428571428571,0.001736111111111111
MixEval,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,2,0.8571428571428571,0.001736111111111111
MixEval,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,3,0.8571428571428571,0.001736111111111111
MixEval,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,4,0.7142857142857142,0.014136904761904762
MixEval Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,0,0.6428571428571428,0.03115079365079365
MixEval Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7857142857142856,0.005505952380952381
MixEval Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,2,0.6428571428571428,0.03115079365079365
MixEval Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,3,0.5714285714285714,0.06101190476190476
MixEval Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,4,0.7142857142857142,0.014136904761904762
MixEval TriviaQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,0,0.6428571428571428,0.03115079365079365
MixEval TriviaQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7857142857142856,0.005505952380952381
MixEval TriviaQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,2,0.4999999999999999,0.10868055555555556
MixEval TriviaQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,3,0.6428571428571428,0.03115079365079365
MixEval TriviaQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,4,0.7857142857142856,0.005505952380952381
MixEval MMLU,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7142857142857142,0.014136904761904762
MixEval MMLU,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,1,0.8571428571428571,0.001736111111111111
MixEval MMLU,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,2,0.8571428571428571,0.001736111111111111
MixEval MMLU,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,3,0.7857142857142856,0.005505952380952381
MixEval MMLU,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,4,0.6428571428571428,0.03115079365079365
MixEval DROP,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,0,0.6182840223353117,0.0340492747686748
MixEval DROP,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,1,0.18184824186332696,0.5330356744917513
MixEval DROP,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,2,0.3571428571428571,0.27509920634920637
MixEval DROP,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,3,0.7857142857142856,0.005505952380952381
MixEval DROP,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,4,0.42857142857142855,0.17886904761904762
MixEval HellaSwag,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,0,0.6428571428571428,0.03115079365079365
MixEval HellaSwag,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,1,0.5714285714285714,0.06101190476190476
MixEval HellaSwag,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7142857142857142,0.014136904761904762
MixEval HellaSwag,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,3,0.5714285714285714,0.06101190476190476
MixEval HellaSwag,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,4,0.42857142857142855,0.17886904761904762
MixEval CommonsenseQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,0,0.6910233190806425,0.017844011512848347
MixEval CommonsenseQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,1,0.5455447255899809,0.0614649096074132
MixEval CommonsenseQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,2,0.5455447255899809,0.0614649096074132
MixEval CommonsenseQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,3,0.836501912571304,0.004136737098676645
MixEval CommonsenseQA,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,4,0.6910233190806425,0.017844011512848347
MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7857142857142856,0.005505952380952381
MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7142857142857142,0.014136904761904762
MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,2,0.4999999999999999,0.10868055555555556
MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,3,0.21428571428571427,0.5484126984126985
MixEval TriviaQA Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,4,0.42857142857142855,0.17886904761904762
MixEval MMLU Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,0,0.4999999999999999,0.10868055555555556
MixEval MMLU Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,1,0.6428571428571428,0.03115079365079365
MixEval MMLU Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,2,0.22237479499833035,0.45088703102517036
MixEval MMLU Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,3,0.3571428571428571,0.27509920634920637
MixEval MMLU Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,4,0.5714285714285714,0.06101190476190476
MixEval DROP Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,0,0.14285714285714285,0.7195436507936508
MixEval DROP Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7142857142857142,0.014136904761904762
MixEval DROP Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,2,0.4999999999999999,0.10868055555555556
MixEval DROP Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,3,0.7142857142857142,0.014136904761904762
MixEval DROP Hard,mixeval_240829.csv,aggregate,aggregate,kendall,random,8,4,0.6428571428571428,0.03115079365079365
AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7857142857142856,0.005505952380952381
AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,aggregate,aggregate,kendall,random,8,1,0.836501912571304,0.004136737098676645
AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7857142857142856,0.005505952380952381
AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,aggregate,aggregate,kendall,random,8,3,0.7857142857142856,0.005505952380952381
AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,aggregate,aggregate,kendall,random,8,4,0.8571428571428571,0.001736111111111111
OpenCompass Arena,opencompass_arena_240829.csv,aggregate,aggregate,kendall,random,8,0,0.2857142857142857,0.39875992063492066
OpenCompass Arena,opencompass_arena_240829.csv,aggregate,aggregate,kendall,random,8,1,0.5714285714285714,0.06101190476190476
OpenCompass Arena,opencompass_arena_240829.csv,aggregate,aggregate,kendall,random,8,2,0.5714285714285714,0.06101190476190476
OpenCompass Arena,opencompass_arena_240829.csv,aggregate,aggregate,kendall,random,8,3,0.3571428571428571,0.27509920634920637
OpenCompass Arena,opencompass_arena_240829.csv,aggregate,aggregate,kendall,random,8,4,0.4999999999999999,0.10868055555555556
LiveBench 240725,livebench_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7142857142857142,0.014136904761904762
LiveBench 240725,livebench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7857142857142856,0.005505952380952381
LiveBench 240725,livebench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.9285714285714285,0.0003968253968253968
LiveBench 240725,livebench_240829.csv,aggregate,aggregate,kendall,random,8,3,0.8571428571428571,0.001736111111111111
LiveBench 240725,livebench_240829.csv,aggregate,aggregate,kendall,random,8,4,0.7857142857142856,0.005505952380952381
LiveBench Reasoning,livebench_240829.csv,aggregate,aggregate,kendall,random,8,0,0.4999999999999999,0.10868055555555556
LiveBench Reasoning,livebench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.3571428571428571,0.27509920634920637
LiveBench Reasoning,livebench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.47280542884465016,0.10506382347888965
LiveBench Reasoning,livebench_240829.csv,aggregate,aggregate,kendall,random,8,3,0.8571428571428571,0.001736111111111111
LiveBench Reasoning,livebench_240829.csv,aggregate,aggregate,kendall,random,8,4,0.5455447255899809,0.0614649096074132
LiveBench Coding,livebench_240829.csv,aggregate,aggregate,kendall,random,8,0,0.9999999999999998,4.96031746031746e-05
LiveBench Coding,livebench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7142857142857142,0.014136904761904762
LiveBench Coding,livebench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.9285714285714285,0.0003968253968253968
LiveBench Coding,livebench_240829.csv,aggregate,aggregate,kendall,random,8,3,0.7857142857142856,0.005505952380952381
LiveBench Coding,livebench_240829.csv,aggregate,aggregate,kendall,random,8,4,0.6428571428571428,0.03115079365079365
LiveBench Mathematics,livebench_240829.csv,aggregate,aggregate,kendall,random,8,0,0.5714285714285714,0.06101190476190476
LiveBench Mathematics,livebench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.5714285714285714,0.06101190476190476
LiveBench Mathematics,livebench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7857142857142856,0.005505952380952381
LiveBench Mathematics,livebench_240829.csv,aggregate,aggregate,kendall,random,8,3,0.9285714285714285,0.0003968253968253968
LiveBench Mathematics,livebench_240829.csv,aggregate,aggregate,kendall,random,8,4,0.7142857142857142,0.014136904761904762
LiveBench Data Analysis,livebench_240829.csv,aggregate,aggregate,kendall,random,8,0,0.4999999999999999,0.10868055555555556
LiveBench Data Analysis,livebench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.6428571428571428,0.03115079365079365
LiveBench Data Analysis,livebench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.8571428571428571,0.001736111111111111
LiveBench Data Analysis,livebench_240829.csv,aggregate,aggregate,kendall,random,8,3,0.7857142857142856,0.005505952380952381
LiveBench Data Analysis,livebench_240829.csv,aggregate,aggregate,kendall,random,8,4,0.6428571428571428,0.03115079365079365
LiveBench Language,livebench_240829.csv,aggregate,aggregate,kendall,random,8,0,0.4999999999999999,0.10868055555555556
LiveBench Language,livebench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.8571428571428571,0.001736111111111111
LiveBench Language,livebench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.4999999999999999,0.10868055555555556
LiveBench Language,livebench_240829.csv,aggregate,aggregate,kendall,random,8,3,0.9285714285714285,0.0003968253968253968
LiveBench Language,livebench_240829.csv,aggregate,aggregate,kendall,random,8,4,0.7857142857142856,0.005505952380952381
LiveBench Instruction Following,livebench_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7142857142857142,0.014136904761904762
LiveBench Instruction Following,livebench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.6428571428571428,0.03115079365079365
LiveBench Instruction Following,livebench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.6428571428571428,0.03115079365079365
LiveBench Instruction Following,livebench_240829.csv,aggregate,aggregate,kendall,random,8,3,0.3571428571428571,0.27509920634920637
LiveBench Instruction Following,livebench_240829.csv,aggregate,aggregate,kendall,random,8,4,0.42857142857142855,0.17886904761904762
WildBench Elo LC,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,0,0.8571428571428571,0.001736111111111111
WildBench Elo LC,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7142857142857142,0.014136904761904762
WildBench Elo LC,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.8571428571428571,0.001736111111111111
WildBench Elo LC,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,3,0.8571428571428571,0.001736111111111111
WildBench Elo LC,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,4,0.6428571428571428,0.03115079365079365
WildBench Information Seeking,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7142857142857142,0.014136904761904762
WildBench Information Seeking,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7857142857142856,0.005505952380952381
WildBench Information Seeking,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.8571428571428571,0.001736111111111111
WildBench Information Seeking,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,3,0.7857142857142856,0.005505952380952381
WildBench Information Seeking,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,4,0.6428571428571428,0.03115079365079365
WildBench Creative,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7857142857142856,0.005505952380952381
WildBench Creative,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7142857142857142,0.014136904761904762
WildBench Creative,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7857142857142856,0.005505952380952381
WildBench Creative,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,3,0.7857142857142856,0.005505952380952381
WildBench Creative,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,4,0.6428571428571428,0.03115079365079365
WildBench Code Debugging,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,0,0.9999999999999998,4.96031746031746e-05
WildBench Code Debugging,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.9999999999999998,4.96031746031746e-05
WildBench Code Debugging,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7857142857142856,0.005505952380952381
WildBench Code Debugging,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,3,0.9285714285714285,0.0003968253968253968
WildBench Code Debugging,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,4,0.9999999999999998,4.96031746031746e-05
WildBench Math & Data,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,0,0.9999999999999998,4.96031746031746e-05
WildBench Math & Data,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.9999999999999998,4.96031746031746e-05
WildBench Math & Data,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.8571428571428571,0.001736111111111111
WildBench Math & Data,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,3,0.9285714285714285,0.0003968253968253968
WildBench Math & Data,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,4,0.9999999999999998,4.96031746031746e-05
WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,0,0.9285714285714285,0.0003968253968253968
WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.9999999999999998,4.96031746031746e-05
WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.8571428571428571,0.001736111111111111
WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,3,0.8571428571428571,0.001736111111111111
WildBench Reasoning & Planning,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,4,0.9285714285714285,0.0003968253968253968
WildBench Score,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,0,0.9999999999999998,4.96031746031746e-05
WildBench Score,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,1,0.9999999999999998,4.96031746031746e-05
WildBench Score,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,2,0.8571428571428571,0.001736111111111111
WildBench Score,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,3,0.8571428571428571,0.001736111111111111
WildBench Score,wildbench_240829.csv,aggregate,aggregate,kendall,random,8,4,0.9999999999999998,4.96031746031746e-05
Arena Hard,arena_hard_240829.csv,aggregate,aggregate,kendall,random,8,0,0.9999999999999998,4.96031746031746e-05
Arena Hard,arena_hard_240829.csv,aggregate,aggregate,kendall,random,8,1,0.9999999999999998,4.96031746031746e-05
Arena Hard,arena_hard_240829.csv,aggregate,aggregate,kendall,random,8,2,0.9999999999999998,4.96031746031746e-05
Arena Hard,arena_hard_240829.csv,aggregate,aggregate,kendall,random,8,3,0.9999999999999998,4.96031746031746e-05
Arena Hard,arena_hard_240829.csv,aggregate,aggregate,kendall,random,8,4,0.9999999999999998,4.96031746031746e-05
HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,0,0.14285714285714285,0.7195436507936508
HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,1,0.4999999999999999,0.10868055555555556
HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,2,0.6428571428571428,0.03115079365079365
HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,3,0.6428571428571428,0.03115079365079365
HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,4,0.5714285714285714,0.06101190476190476
HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,0,0.4999999999999999,0.10868055555555556
HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,1,0.42857142857142855,0.17886904761904762
HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,2,0.7857142857142856,0.005505952380952381
HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,3,0.5714285714285714,0.06101190476190476
HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,4,0.3571428571428571,0.27509920634920637
HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,0,0.0,1.0
HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,1,0.5714285714285714,0.06101190476190476
HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,2,0.5714285714285714,0.06101190476190476
HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,3,0.6428571428571428,0.03115079365079365
HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,4,0.6428571428571428,0.03115079365079365
HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,0,0.5714285714285714,0.06101190476190476
HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,1,0.10910894511799618,0.7083840532183997
HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,2,0.6182840223353117,0.0340492747686748
HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,3,0.2857142857142857,0.39875992063492066
HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,4,0.40006613209931935,0.17023995462900499
HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,0,0.5714285714285714,0.06101190476190476
HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,1,0.7857142857142856,0.005505952380952381
HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,2,0.7857142857142856,0.005505952380952381
HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,3,0.9285714285714285,0.0003968253968253968
HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,4,0.7857142857142856,0.005505952380952381
HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,0,0.4999999999999999,0.10868055555555556
HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,1,0.2857142857142857,0.39875992063492066
HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,2,0.6428571428571428,0.03115079365079365
HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,3,0.42857142857142855,0.17886904761904762
HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,4,0.3571428571428571,0.27509920634920637
HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,0,0.42857142857142855,0.17886904761904762
HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,1,0.2857142857142857,0.39875992063492066
HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,2,0.6182840223353117,0.0340492747686748
HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,3,0.42857142857142855,0.17886904761904762
HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,aggregate,aggregate,kendall,random,8,4,0.2857142857142857,0.39875992063492066
BFCL,bfcl_240906.csv,aggregate,aggregate,kendall,random,8,0,0.21428571428571427,0.5484126984126985
BFCL,bfcl_240906.csv,aggregate,aggregate,kendall,random,8,1,0.14285714285714285,0.7195436507936508
BFCL,bfcl_240906.csv,aggregate,aggregate,kendall,random,8,2,0.42857142857142855,0.17886904761904762
BFCL,bfcl_240906.csv,aggregate,aggregate,kendall,random,8,3,0.4999999999999999,0.10868055555555556
BFCL,bfcl_240906.csv,aggregate,aggregate,kendall,random,8,4,0.3571428571428571,0.27509920634920637
BIGGEN,biggen_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7142857142857142,0.014136904761904762
BIGGEN,biggen_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7857142857142856,0.005505952380952381
BIGGEN,biggen_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7857142857142856,0.005505952380952381
BIGGEN,biggen_240829.csv,aggregate,aggregate,kendall,random,8,3,0.7142857142857142,0.014136904761904762
BIGGEN,biggen_240829.csv,aggregate,aggregate,kendall,random,8,4,0.7142857142857142,0.014136904761904762
BIGGEN Grounding,biggen_240829.csv,aggregate,aggregate,kendall,random,8,0,0.6428571428571428,0.03115079365079365
BIGGEN Grounding,biggen_240829.csv,aggregate,aggregate,kendall,random,8,1,0.8571428571428571,0.001736111111111111
BIGGEN Grounding,biggen_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7142857142857142,0.014136904761904762
BIGGEN Grounding,biggen_240829.csv,aggregate,aggregate,kendall,random,8,3,0.7857142857142856,0.005505952380952381
BIGGEN Grounding,biggen_240829.csv,aggregate,aggregate,kendall,random,8,4,0.6428571428571428,0.03115079365079365
BIGGEN Instruction Following,biggen_240829.csv,aggregate,aggregate,kendall,random,8,0,0.40006613209931935,0.17023995462900499
BIGGEN Instruction Following,biggen_240829.csv,aggregate,aggregate,kendall,random,8,1,0.6910233190806425,0.017844011512848347
BIGGEN Instruction Following,biggen_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7142857142857142,0.014136904761904762
BIGGEN Instruction Following,biggen_240829.csv,aggregate,aggregate,kendall,random,8,3,0.7142857142857142,0.014136904761904762
BIGGEN Instruction Following,biggen_240829.csv,aggregate,aggregate,kendall,random,8,4,0.47280542884465016,0.10506382347888965
BIGGEN Planning,biggen_240829.csv,aggregate,aggregate,kendall,random,8,0,0.47280542884465016,0.10506382347888965
BIGGEN Planning,biggen_240829.csv,aggregate,aggregate,kendall,random,8,1,0.42857142857142855,0.17886904761904762
BIGGEN Planning,biggen_240829.csv,aggregate,aggregate,kendall,random,8,2,0.7637626158259734,0.008839740160738534
BIGGEN Planning,biggen_240829.csv,aggregate,aggregate,kendall,random,8,3,0.5714285714285714,0.06101190476190476
BIGGEN Planning,biggen_240829.csv,aggregate,aggregate,kendall,random,8,4,0.10910894511799618,0.7083840532183997
BIGGEN Reasoning,biggen_240829.csv,aggregate,aggregate,kendall,random,8,0,0.8571428571428571,0.001736111111111111
BIGGEN Reasoning,biggen_240829.csv,aggregate,aggregate,kendall,random,8,1,0.9285714285714285,0.0003968253968253968
BIGGEN Reasoning,biggen_240829.csv,aggregate,aggregate,kendall,random,8,2,0.9999999999999998,4.96031746031746e-05
BIGGEN Reasoning,biggen_240829.csv,aggregate,aggregate,kendall,random,8,3,0.5714285714285714,0.06101190476190476
BIGGEN Reasoning,biggen_240829.csv,aggregate,aggregate,kendall,random,8,4,0.8571428571428571,0.001736111111111111
BIGGEN Refinement,biggen_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7857142857142856,0.005505952380952381
BIGGEN Refinement,biggen_240829.csv,aggregate,aggregate,kendall,random,8,1,0.7637626158259734,0.008839740160738534
BIGGEN Refinement,biggen_240829.csv,aggregate,aggregate,kendall,random,8,2,0.9285714285714285,0.0003968253968253968
BIGGEN Refinement,biggen_240829.csv,aggregate,aggregate,kendall,random,8,3,0.6428571428571428,0.03115079365079365
BIGGEN Refinement,biggen_240829.csv,aggregate,aggregate,kendall,random,8,4,0.7637626158259734,0.008839740160738534
BIGGEN Safety,biggen_240829.csv,aggregate,aggregate,kendall,random,8,0,-0.2857142857142857,0.39875992063492066
BIGGEN Safety,biggen_240829.csv,aggregate,aggregate,kendall,random,8,1,0.2545875386086578,0.38281014365989596
BIGGEN Safety,biggen_240829.csv,aggregate,aggregate,kendall,random,8,2,0.6910233190806425,0.017844011512848347
BIGGEN Safety,biggen_240829.csv,aggregate,aggregate,kendall,random,8,3,0.10910894511799618,0.7083840532183997
BIGGEN Safety,biggen_240829.csv,aggregate,aggregate,kendall,random,8,4,0.07142857142857142,0.9048611111111111
BIGGEN Theory of Mind,biggen_240829.csv,aggregate,aggregate,kendall,random,8,0,0.4999999999999999,0.10868055555555556
BIGGEN Theory of Mind,biggen_240829.csv,aggregate,aggregate,kendall,random,8,1,0.6428571428571428,0.03115079365079365
BIGGEN Theory of Mind,biggen_240829.csv,aggregate,aggregate,kendall,random,8,2,0.836501912571304,0.004136737098676645
BIGGEN Theory of Mind,biggen_240829.csv,aggregate,aggregate,kendall,random,8,3,0.5669467095138409,0.05611472402809984
BIGGEN Theory of Mind,biggen_240829.csv,aggregate,aggregate,kendall,random,8,4,0.6182840223353117,0.0340492747686748
BIGGEN Tool Usage,biggen_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7142857142857142,0.014136904761904762
BIGGEN Tool Usage,biggen_240829.csv,aggregate,aggregate,kendall,random,8,1,0.4999999999999999,0.10868055555555556
BIGGEN Tool Usage,biggen_240829.csv,aggregate,aggregate,kendall,random,8,2,0.5714285714285714,0.06101190476190476
BIGGEN Tool Usage,biggen_240829.csv,aggregate,aggregate,kendall,random,8,3,0.6428571428571428,0.03115079365079365
BIGGEN Tool Usage,biggen_240829.csv,aggregate,aggregate,kendall,random,8,4,0.42857142857142855,0.17886904761904762
BIGGEN Multilingual,biggen_240829.csv,aggregate,aggregate,kendall,random,8,0,0.7142857142857142,0.014136904761904762
BIGGEN Multilingual,biggen_240829.csv,aggregate,aggregate,kendall,random,8,1,0.8571428571428571,0.001736111111111111
BIGGEN Multilingual,biggen_240829.csv,aggregate,aggregate,kendall,random,8,2,0.42857142857142855,0.17886904761904762
BIGGEN Multilingual,biggen_240829.csv,aggregate,aggregate,kendall,random,8,3,0.6428571428571428,0.03115079365079365
BIGGEN Multilingual,biggen_240829.csv,aggregate,aggregate,kendall,random,8,4,0.8571428571428571,0.001736111111111111
LiveBench 240624,livebench_240701.csv,aggregate,aggregate,kendall,random,8,0,0.7142857142857142,0.014136904761904762
LiveBench 240624,livebench_240701.csv,aggregate,aggregate,kendall,random,8,1,0.9999999999999998,4.96031746031746e-05
LiveBench 240624,livebench_240701.csv,aggregate,aggregate,kendall,random,8,2,0.8571428571428571,0.001736111111111111
LiveBench 240624,livebench_240701.csv,aggregate,aggregate,kendall,random,8,3,0.8571428571428571,0.001736111111111111
LiveBench 240624,livebench_240701.csv,aggregate,aggregate,kendall,random,8,4,0.7857142857142856,0.005505952380952381
LiveBench Reasoning Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,0,0.7412493166611012,0.011966745157436277
LiveBench Reasoning Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,1,0.8571428571428571,0.001736111111111111
LiveBench Reasoning Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,2,0.7637626158259734,0.008839740160738534
LiveBench Reasoning Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,3,0.7142857142857142,0.014136904761904762
LiveBench Reasoning Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,4,0.8571428571428571,0.001736111111111111
LiveBench Coding Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,0,0.6428571428571428,0.03115079365079365
LiveBench Coding Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,1,0.9285714285714285,0.0003968253968253968
LiveBench Coding Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,2,0.7857142857142856,0.005505952380952381
LiveBench Coding Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,3,0.9999999999999998,4.96031746031746e-05
LiveBench Coding Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,4,0.7637626158259734,0.008839740160738534
LiveBench Mathematics Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,0,0.7142857142857142,0.014136904761904762
LiveBench Mathematics Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,1,0.9999999999999998,4.96031746031746e-05
LiveBench Mathematics Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,2,0.7142857142857142,0.014136904761904762
LiveBench Mathematics Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,3,0.8571428571428571,0.001736111111111111
LiveBench Mathematics Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,4,0.8571428571428571,0.001736111111111111
LiveBench Data Analysis Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,0,0.4999999999999999,0.10868055555555556
LiveBench Data Analysis Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,1,0.8571428571428571,0.001736111111111111
LiveBench Data Analysis Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,2,0.7142857142857142,0.014136904761904762
LiveBench Data Analysis Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,3,0.7857142857142856,0.005505952380952381
LiveBench Data Analysis Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,4,0.6428571428571428,0.03115079365079365
LiveBench Language Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,0,0.6428571428571428,0.03115079365079365
LiveBench Language Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,1,0.9999999999999998,4.96031746031746e-05
LiveBench Language Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,2,0.7142857142857142,0.014136904761904762
LiveBench Language Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,3,0.7857142857142856,0.005505952380952381
LiveBench Language Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,4,0.8571428571428571,0.001736111111111111
LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,0,0.5714285714285714,0.06101190476190476
LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,1,0.8571428571428571,0.001736111111111111
LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,2,0.7857142857142856,0.005505952380952381
LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,3,0.5714285714285714,0.06101190476190476
LiveBench Instruction Following Average,livebench_240701.csv,aggregate,aggregate,kendall,random,8,4,0.7857142857142856,0.005505952380952381
aggregate,aggregate,Helm Lite,helm_lite_240829.csv,kendall,random,8,0,0.4447495899966607,0.1315867602811863
aggregate,aggregate,Helm Lite,helm_lite_240829.csv,kendall,random,8,1,0.3571428571428571,0.27509920634920637
aggregate,aggregate,Helm Lite,helm_lite_240829.csv,kendall,random,8,2,0.47280542884465016,0.10506382347888965
aggregate,aggregate,Helm Lite,helm_lite_240829.csv,kendall,random,8,3,0.2545875386086578,0.38281014365989596
aggregate,aggregate,Helm Lite,helm_lite_240829.csv,kendall,random,8,4,0.40006613209931935,0.17023995462900499
aggregate,aggregate,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,8,0,0.07142857142857142,0.9048611111111111
aggregate,aggregate,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,8,1,-0.2857142857142857,0.39875992063492066
aggregate,aggregate,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,8,2,0.07142857142857142,0.9048611111111111
aggregate,aggregate,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,8,3,-0.21428571428571427,0.5484126984126985
aggregate,aggregate,Helm Lite NarrativeQA,helm_lite_240829.csv,kendall,random,8,4,-0.3571428571428571,0.27509920634920637
aggregate,aggregate,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,8,0,0.07142857142857142,0.9048611111111111
aggregate,aggregate,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,8,1,-0.2857142857142857,0.39875992063492066
aggregate,aggregate,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,8,2,0.14285714285714285,0.7195436507936508
aggregate,aggregate,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,8,3,-0.21428571428571427,0.5484126984126985
aggregate,aggregate,Helm Lite NaturalQuestionsOpen,helm_lite_240829.csv,kendall,random,8,4,-0.2857142857142857,0.39875992063492066
aggregate,aggregate,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,8,0,0.21428571428571427,0.5484126984126985
aggregate,aggregate,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,8,1,0.0,1.0
aggregate,aggregate,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,8,2,0.3571428571428571,0.27509920634920637
aggregate,aggregate,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,8,3,0.0,1.0
aggregate,aggregate,Helm Lite NaturalQuestionsClosed,helm_lite_240829.csv,kendall,random,8,4,0.0,1.0
aggregate,aggregate,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,8,0,0.7637626158259734,0.008839740160738534
aggregate,aggregate,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,8,1,0.7857142857142856,0.005505952380952381
aggregate,aggregate,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,8,2,0.7857142857142856,0.005505952380952381
aggregate,aggregate,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,8,3,0.5714285714285714,0.06101190476190476
aggregate,aggregate,Helm Lite OpenBookQA,helm_lite_240829.csv,kendall,random,8,4,0.7637626158259734,0.008839740160738534
aggregate,aggregate,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,8,0,0.7142857142857142,0.014136904761904762
aggregate,aggregate,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,8,1,0.7857142857142856,0.005505952380952381
aggregate,aggregate,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,8,2,0.6428571428571428,0.03115079365079365
aggregate,aggregate,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,8,3,0.5714285714285714,0.06101190476190476
aggregate,aggregate,Helm Lite MMLU,helm_lite_240829.csv,kendall,random,8,4,0.7142857142857142,0.014136904761904762
aggregate,aggregate,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,8,0,0.21428571428571427,0.5484126984126985
aggregate,aggregate,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,8,1,0.2857142857142857,0.39875992063492066
aggregate,aggregate,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,8,2,0.4999999999999999,0.10868055555555556
aggregate,aggregate,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,8,3,0.14285714285714285,0.7195436507936508
aggregate,aggregate,Helm Lite MathEquivalentCOT,helm_lite_240829.csv,kendall,random,8,4,0.3571428571428571,0.27509920634920637
aggregate,aggregate,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,8,0,0.5714285714285714,0.06101190476190476
aggregate,aggregate,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,8,1,0.8571428571428571,0.001736111111111111
aggregate,aggregate,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,8,2,0.7142857142857142,0.014136904761904762
aggregate,aggregate,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,8,3,0.7857142857142856,0.005505952380952381
aggregate,aggregate,Helm Lite GSM8K,helm_lite_240829.csv,kendall,random,8,4,0.7142857142857142,0.014136904761904762
aggregate,aggregate,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,8,0,0.2857142857142857,0.39875992063492066
aggregate,aggregate,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,8,1,0.21428571428571427,0.5484126984126985
aggregate,aggregate,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,8,2,0.3571428571428571,0.27509920634920637
aggregate,aggregate,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,8,3,0.036369648372665396,0.9007802600472398
aggregate,aggregate,Helm Lite LegalBench,helm_lite_240829.csv,kendall,random,8,4,0.21428571428571427,0.5484126984126985
aggregate,aggregate,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,8,0,0.6428571428571428,0.03115079365079365
aggregate,aggregate,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,8,1,0.6428571428571428,0.03115079365079365
aggregate,aggregate,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,8,2,0.4999999999999999,0.10868055555555556
aggregate,aggregate,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,8,3,0.5714285714285714,0.06101190476190476
aggregate,aggregate,Helm Lite MedQA,helm_lite_240829.csv,kendall,random,8,4,0.6428571428571428,0.03115079365079365
aggregate,aggregate,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,8,0,0.6428571428571428,0.03115079365079365
aggregate,aggregate,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,8,1,0.3571428571428571,0.27509920634920637
aggregate,aggregate,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,8,2,0.42857142857142855,0.17886904761904762
aggregate,aggregate,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,8,3,0.3571428571428571,0.27509920634920637
aggregate,aggregate,Helm Lite WMT2014,helm_lite_240829.csv,kendall,random,8,4,0.3571428571428571,0.27509920634920637
aggregate,aggregate,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,8,0,0.9285714285714285,0.0003968253968253968
aggregate,aggregate,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,8,1,0.9285714285714285,0.0003968253968253968
aggregate,aggregate,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,8,2,0.9285714285714285,0.0003968253968253968
aggregate,aggregate,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,8,3,0.9285714285714285,0.0003968253968253968
aggregate,aggregate,HF OpenLLM v2,hf_open_llm_v2_240829.csv,kendall,random,8,4,0.9285714285714285,0.0003968253968253968
aggregate,aggregate,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,8,0,0.7857142857142856,0.005505952380952381
aggregate,aggregate,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,8,1,0.7857142857142856,0.005505952380952381
aggregate,aggregate,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,8,2,0.9999999999999998,4.96031746031746e-05
aggregate,aggregate,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,8,3,0.7142857142857142,0.014136904761904762
aggregate,aggregate,HFv2 BBH,hf_open_llm_v2_240829.csv,kendall,random,8,4,0.8571428571428571,0.001736111111111111
aggregate,aggregate,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,8,0,0.4999999999999999,0.10868055555555556
aggregate,aggregate,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,8,1,0.4999999999999999,0.10868055555555556
aggregate,aggregate,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,8,2,0.7857142857142856,0.005505952380952381
aggregate,aggregate,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,8,3,0.7857142857142856,0.005505952380952381
aggregate,aggregate,HFv2 GPQA,hf_open_llm_v2_240829.csv,kendall,random,8,4,0.3571428571428571,0.27509920634920637
aggregate,aggregate,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,8,0,0.8571428571428571,0.001736111111111111
aggregate,aggregate,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,8,1,0.4999999999999999,0.10868055555555556
aggregate,aggregate,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,8,2,0.7857142857142856,0.005505952380952381
aggregate,aggregate,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,8,3,0.5714285714285714,0.06101190476190476
aggregate,aggregate,HFv2 IFEval,hf_open_llm_v2_240829.csv,kendall,random,8,4,0.7142857142857142,0.014136904761904762
aggregate,aggregate,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,8,0,0.9285714285714285,0.0003968253968253968
aggregate,aggregate,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,8,1,0.9285714285714285,0.0003968253968253968
aggregate,aggregate,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,8,2,0.9999999999999998,4.96031746031746e-05
aggregate,aggregate,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,8,3,0.8571428571428571,0.001736111111111111
aggregate,aggregate,HFv2 MMLU Pro,hf_open_llm_v2_240829.csv,kendall,random,8,4,0.8571428571428571,0.001736111111111111
aggregate,aggregate,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,8,0,0.8571428571428571,0.001736111111111111
aggregate,aggregate,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,8,1,0.5714285714285714,0.06101190476190476
aggregate,aggregate,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,8,2,0.7857142857142856,0.005505952380952381
aggregate,aggregate,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,8,3,0.4999999999999999,0.10868055555555556
aggregate,aggregate,HFv2 Math Level 5,hf_open_llm_v2_240829.csv,kendall,random,8,4,0.9285714285714285,0.0003968253968253968
aggregate,aggregate,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,8,0,0.7142857142857142,0.014136904761904762
aggregate,aggregate,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,8,1,0.4999999999999999,0.10868055555555556
aggregate,aggregate,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,8,2,0.5714285714285714,0.06101190476190476
aggregate,aggregate,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,8,3,0.7857142857142856,0.005505952380952381
aggregate,aggregate,HFv2 MuSR,hf_open_llm_v2_240829.csv,kendall,random,8,4,0.6428571428571428,0.03115079365079365
aggregate,aggregate,Helm MMLU,helm_mmlu_240829.csv,kendall,random,8,0,0.5714285714285714,0.06101190476190476
aggregate,aggregate,Helm MMLU,helm_mmlu_240829.csv,kendall,random,8,1,0.7142857142857142,0.014136904761904762
aggregate,aggregate,Helm MMLU,helm_mmlu_240829.csv,kendall,random,8,2,0.7142857142857142,0.014136904761904762
aggregate,aggregate,Helm MMLU,helm_mmlu_240829.csv,kendall,random,8,3,0.7857142857142856,0.005505952380952381
aggregate,aggregate,Helm MMLU,helm_mmlu_240829.csv,kendall,random,8,4,0.7857142857142856,0.005505952380952381
aggregate,aggregate,LMSys Arena,chatbot_arena_240829.csv,kendall,random,8,0,0.9999999999999998,4.96031746031746e-05
aggregate,aggregate,LMSys Arena,chatbot_arena_240829.csv,kendall,random,8,1,0.9999999999999998,4.96031746031746e-05
aggregate,aggregate,LMSys Arena,chatbot_arena_240829.csv,kendall,random,8,2,0.9999999999999998,4.96031746031746e-05
aggregate,aggregate,LMSys Arena,chatbot_arena_240829.csv,kendall,random,8,3,0.9999999999999998,4.96031746031746e-05
aggregate,aggregate,LMSys Arena,chatbot_arena_240829.csv,kendall,random,8,4,0.9999999999999998,4.96031746031746e-05
aggregate,aggregate,MMLU Pro,mmlu_pro_240829.csv,kendall,random,8,0,0.8571428571428571,0.001736111111111111
aggregate,aggregate,MMLU Pro,mmlu_pro_240829.csv,kendall,random,8,1,0.9285714285714285,0.0003968253968253968
aggregate,aggregate,MMLU Pro,mmlu_pro_240829.csv,kendall,random,8,2,0.8571428571428571,0.001736111111111111
aggregate,aggregate,MMLU Pro,mmlu_pro_240829.csv,kendall,random,8,3,0.9285714285714285,0.0003968253968253968
aggregate,aggregate,MMLU Pro,mmlu_pro_240829.csv,kendall,random,8,4,0.9285714285714285,0.0003968253968253968
aggregate,aggregate,MixEval,mixeval_240829.csv,kendall,random,8,0,0.7857142857142856,0.005505952380952381
aggregate,aggregate,MixEval,mixeval_240829.csv,kendall,random,8,1,0.8571428571428571,0.001736111111111111
aggregate,aggregate,MixEval,mixeval_240829.csv,kendall,random,8,2,0.8571428571428571,0.001736111111111111
aggregate,aggregate,MixEval,mixeval_240829.csv,kendall,random,8,3,0.8571428571428571,0.001736111111111111
aggregate,aggregate,MixEval,mixeval_240829.csv,kendall,random,8,4,0.7142857142857142,0.014136904761904762
aggregate,aggregate,MixEval Hard,mixeval_240829.csv,kendall,random,8,0,0.6428571428571428,0.03115079365079365
aggregate,aggregate,MixEval Hard,mixeval_240829.csv,kendall,random,8,1,0.7857142857142856,0.005505952380952381
aggregate,aggregate,MixEval Hard,mixeval_240829.csv,kendall,random,8,2,0.6428571428571428,0.03115079365079365
aggregate,aggregate,MixEval Hard,mixeval_240829.csv,kendall,random,8,3,0.5714285714285714,0.06101190476190476
aggregate,aggregate,MixEval Hard,mixeval_240829.csv,kendall,random,8,4,0.7142857142857142,0.014136904761904762
aggregate,aggregate,MixEval TriviaQA,mixeval_240829.csv,kendall,random,8,0,0.6428571428571428,0.03115079365079365
aggregate,aggregate,MixEval TriviaQA,mixeval_240829.csv,kendall,random,8,1,0.7857142857142856,0.005505952380952381
aggregate,aggregate,MixEval TriviaQA,mixeval_240829.csv,kendall,random,8,2,0.4999999999999999,0.10868055555555556
aggregate,aggregate,MixEval TriviaQA,mixeval_240829.csv,kendall,random,8,3,0.6428571428571428,0.03115079365079365
aggregate,aggregate,MixEval TriviaQA,mixeval_240829.csv,kendall,random,8,4,0.7857142857142856,0.005505952380952381
aggregate,aggregate,MixEval MMLU,mixeval_240829.csv,kendall,random,8,0,0.7142857142857142,0.014136904761904762
aggregate,aggregate,MixEval MMLU,mixeval_240829.csv,kendall,random,8,1,0.8571428571428571,0.001736111111111111
aggregate,aggregate,MixEval MMLU,mixeval_240829.csv,kendall,random,8,2,0.8571428571428571,0.001736111111111111
aggregate,aggregate,MixEval MMLU,mixeval_240829.csv,kendall,random,8,3,0.7857142857142856,0.005505952380952381
aggregate,aggregate,MixEval MMLU,mixeval_240829.csv,kendall,random,8,4,0.6428571428571428,0.03115079365079365
aggregate,aggregate,MixEval DROP,mixeval_240829.csv,kendall,random,8,0,0.6182840223353117,0.0340492747686748
aggregate,aggregate,MixEval DROP,mixeval_240829.csv,kendall,random,8,1,0.18184824186332696,0.5330356744917513
aggregate,aggregate,MixEval DROP,mixeval_240829.csv,kendall,random,8,2,0.3571428571428571,0.27509920634920637
aggregate,aggregate,MixEval DROP,mixeval_240829.csv,kendall,random,8,3,0.7857142857142856,0.005505952380952381
aggregate,aggregate,MixEval DROP,mixeval_240829.csv,kendall,random,8,4,0.42857142857142855,0.17886904761904762
aggregate,aggregate,MixEval HellaSwag,mixeval_240829.csv,kendall,random,8,0,0.6428571428571428,0.03115079365079365
aggregate,aggregate,MixEval HellaSwag,mixeval_240829.csv,kendall,random,8,1,0.5714285714285714,0.06101190476190476
aggregate,aggregate,MixEval HellaSwag,mixeval_240829.csv,kendall,random,8,2,0.7142857142857142,0.014136904761904762
aggregate,aggregate,MixEval HellaSwag,mixeval_240829.csv,kendall,random,8,3,0.5714285714285714,0.06101190476190476
aggregate,aggregate,MixEval HellaSwag,mixeval_240829.csv,kendall,random,8,4,0.42857142857142855,0.17886904761904762
aggregate,aggregate,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,8,0,0.6910233190806425,0.017844011512848347
aggregate,aggregate,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,8,1,0.5455447255899809,0.0614649096074132
aggregate,aggregate,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,8,2,0.5455447255899809,0.0614649096074132
aggregate,aggregate,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,8,3,0.836501912571304,0.004136737098676645
aggregate,aggregate,MixEval CommonsenseQA,mixeval_240829.csv,kendall,random,8,4,0.6910233190806425,0.017844011512848347
aggregate,aggregate,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,8,0,0.7857142857142856,0.005505952380952381
aggregate,aggregate,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,8,1,0.7142857142857142,0.014136904761904762
aggregate,aggregate,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,8,2,0.4999999999999999,0.10868055555555556
aggregate,aggregate,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,8,3,0.21428571428571427,0.5484126984126985
aggregate,aggregate,MixEval TriviaQA Hard,mixeval_240829.csv,kendall,random,8,4,0.42857142857142855,0.17886904761904762
aggregate,aggregate,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,8,0,0.4999999999999999,0.10868055555555556
aggregate,aggregate,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,8,1,0.6428571428571428,0.03115079365079365
aggregate,aggregate,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,8,2,0.22237479499833035,0.45088703102517036
aggregate,aggregate,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,8,3,0.3571428571428571,0.27509920634920637
aggregate,aggregate,MixEval MMLU Hard,mixeval_240829.csv,kendall,random,8,4,0.5714285714285714,0.06101190476190476
aggregate,aggregate,MixEval DROP Hard,mixeval_240829.csv,kendall,random,8,0,0.14285714285714285,0.7195436507936508
aggregate,aggregate,MixEval DROP Hard,mixeval_240829.csv,kendall,random,8,1,0.7142857142857142,0.014136904761904762
aggregate,aggregate,MixEval DROP Hard,mixeval_240829.csv,kendall,random,8,2,0.4999999999999999,0.10868055555555556
aggregate,aggregate,MixEval DROP Hard,mixeval_240829.csv,kendall,random,8,3,0.7142857142857142,0.014136904761904762
aggregate,aggregate,MixEval DROP Hard,mixeval_240829.csv,kendall,random,8,4,0.6428571428571428,0.03115079365079365
aggregate,aggregate,AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,kendall,random,8,0,0.7857142857142856,0.005505952380952381
aggregate,aggregate,AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,kendall,random,8,1,0.836501912571304,0.004136737098676645
aggregate,aggregate,AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,kendall,random,8,2,0.7857142857142856,0.005505952380952381
aggregate,aggregate,AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,kendall,random,8,3,0.7857142857142856,0.005505952380952381
aggregate,aggregate,AlphacaEval v2lc,alphacaeval_v2lc_240829.csv,kendall,random,8,4,0.8571428571428571,0.001736111111111111
aggregate,aggregate,OpenCompass Arena,opencompass_arena_240829.csv,kendall,random,8,0,0.2857142857142857,0.39875992063492066
aggregate,aggregate,OpenCompass Arena,opencompass_arena_240829.csv,kendall,random,8,1,0.5714285714285714,0.06101190476190476
aggregate,aggregate,OpenCompass Arena,opencompass_arena_240829.csv,kendall,random,8,2,0.5714285714285714,0.06101190476190476
aggregate,aggregate,OpenCompass Arena,opencompass_arena_240829.csv,kendall,random,8,3,0.3571428571428571,0.27509920634920637
aggregate,aggregate,OpenCompass Arena,opencompass_arena_240829.csv,kendall,random,8,4,0.4999999999999999,0.10868055555555556
aggregate,aggregate,LiveBench 240725,livebench_240829.csv,kendall,random,8,0,0.7142857142857142,0.014136904761904762
aggregate,aggregate,LiveBench 240725,livebench_240829.csv,kendall,random,8,1,0.7857142857142856,0.005505952380952381
aggregate,aggregate,LiveBench 240725,livebench_240829.csv,kendall,random,8,2,0.9285714285714285,0.0003968253968253968
aggregate,aggregate,LiveBench 240725,livebench_240829.csv,kendall,random,8,3,0.8571428571428571,0.001736111111111111
aggregate,aggregate,LiveBench 240725,livebench_240829.csv,kendall,random,8,4,0.7857142857142856,0.005505952380952381
aggregate,aggregate,LiveBench Reasoning,livebench_240829.csv,kendall,random,8,0,0.4999999999999999,0.10868055555555556
aggregate,aggregate,LiveBench Reasoning,livebench_240829.csv,kendall,random,8,1,0.3571428571428571,0.27509920634920637
aggregate,aggregate,LiveBench Reasoning,livebench_240829.csv,kendall,random,8,2,0.47280542884465016,0.10506382347888965
aggregate,aggregate,LiveBench Reasoning,livebench_240829.csv,kendall,random,8,3,0.8571428571428571,0.001736111111111111
aggregate,aggregate,LiveBench Reasoning,livebench_240829.csv,kendall,random,8,4,0.5455447255899809,0.0614649096074132
aggregate,aggregate,LiveBench Coding,livebench_240829.csv,kendall,random,8,0,0.9999999999999998,4.96031746031746e-05
aggregate,aggregate,LiveBench Coding,livebench_240829.csv,kendall,random,8,1,0.7142857142857142,0.014136904761904762
aggregate,aggregate,LiveBench Coding,livebench_240829.csv,kendall,random,8,2,0.9285714285714285,0.0003968253968253968
aggregate,aggregate,LiveBench Coding,livebench_240829.csv,kendall,random,8,3,0.7857142857142856,0.005505952380952381
aggregate,aggregate,LiveBench Coding,livebench_240829.csv,kendall,random,8,4,0.6428571428571428,0.03115079365079365
aggregate,aggregate,LiveBench Mathematics,livebench_240829.csv,kendall,random,8,0,0.5714285714285714,0.06101190476190476
aggregate,aggregate,LiveBench Mathematics,livebench_240829.csv,kendall,random,8,1,0.5714285714285714,0.06101190476190476
aggregate,aggregate,LiveBench Mathematics,livebench_240829.csv,kendall,random,8,2,0.7857142857142856,0.005505952380952381
aggregate,aggregate,LiveBench Mathematics,livebench_240829.csv,kendall,random,8,3,0.9285714285714285,0.0003968253968253968
aggregate,aggregate,LiveBench Mathematics,livebench_240829.csv,kendall,random,8,4,0.7142857142857142,0.014136904761904762
aggregate,aggregate,LiveBench Data Analysis,livebench_240829.csv,kendall,random,8,0,0.4999999999999999,0.10868055555555556
aggregate,aggregate,LiveBench Data Analysis,livebench_240829.csv,kendall,random,8,1,0.6428571428571428,0.03115079365079365
aggregate,aggregate,LiveBench Data Analysis,livebench_240829.csv,kendall,random,8,2,0.8571428571428571,0.001736111111111111
aggregate,aggregate,LiveBench Data Analysis,livebench_240829.csv,kendall,random,8,3,0.7857142857142856,0.005505952380952381
aggregate,aggregate,LiveBench Data Analysis,livebench_240829.csv,kendall,random,8,4,0.6428571428571428,0.03115079365079365
aggregate,aggregate,LiveBench Language,livebench_240829.csv,kendall,random,8,0,0.4999999999999999,0.10868055555555556
aggregate,aggregate,LiveBench Language,livebench_240829.csv,kendall,random,8,1,0.8571428571428571,0.001736111111111111
aggregate,aggregate,LiveBench Language,livebench_240829.csv,kendall,random,8,2,0.4999999999999999,0.10868055555555556
aggregate,aggregate,LiveBench Language,livebench_240829.csv,kendall,random,8,3,0.9285714285714285,0.0003968253968253968
aggregate,aggregate,LiveBench Language,livebench_240829.csv,kendall,random,8,4,0.7857142857142856,0.005505952380952381
aggregate,aggregate,LiveBench Instruction Following,livebench_240829.csv,kendall,random,8,0,0.7142857142857142,0.014136904761904762
aggregate,aggregate,LiveBench Instruction Following,livebench_240829.csv,kendall,random,8,1,0.6428571428571428,0.03115079365079365
aggregate,aggregate,LiveBench Instruction Following,livebench_240829.csv,kendall,random,8,2,0.6428571428571428,0.03115079365079365
aggregate,aggregate,LiveBench Instruction Following,livebench_240829.csv,kendall,random,8,3,0.3571428571428571,0.27509920634920637
aggregate,aggregate,LiveBench Instruction Following,livebench_240829.csv,kendall,random,8,4,0.42857142857142855,0.17886904761904762
aggregate,aggregate,WildBench Elo LC,wildbench_240829.csv,kendall,random,8,0,0.8571428571428571,0.001736111111111111
aggregate,aggregate,WildBench Elo LC,wildbench_240829.csv,kendall,random,8,1,0.7142857142857142,0.014136904761904762
aggregate,aggregate,WildBench Elo LC,wildbench_240829.csv,kendall,random,8,2,0.8571428571428571,0.001736111111111111
aggregate,aggregate,WildBench Elo LC,wildbench_240829.csv,kendall,random,8,3,0.8571428571428571,0.001736111111111111
aggregate,aggregate,WildBench Elo LC,wildbench_240829.csv,kendall,random,8,4,0.6428571428571428,0.03115079365079365
aggregate,aggregate,WildBench Information Seeking,wildbench_240829.csv,kendall,random,8,0,0.7142857142857142,0.014136904761904762
aggregate,aggregate,WildBench Information Seeking,wildbench_240829.csv,kendall,random,8,1,0.7857142857142856,0.005505952380952381
aggregate,aggregate,WildBench Information Seeking,wildbench_240829.csv,kendall,random,8,2,0.8571428571428571,0.001736111111111111
aggregate,aggregate,WildBench Information Seeking,wildbench_240829.csv,kendall,random,8,3,0.7857142857142856,0.005505952380952381
aggregate,aggregate,WildBench Information Seeking,wildbench_240829.csv,kendall,random,8,4,0.6428571428571428,0.03115079365079365
aggregate,aggregate,WildBench Creative,wildbench_240829.csv,kendall,random,8,0,0.7857142857142856,0.005505952380952381
aggregate,aggregate,WildBench Creative,wildbench_240829.csv,kendall,random,8,1,0.7142857142857142,0.014136904761904762
aggregate,aggregate,WildBench Creative,wildbench_240829.csv,kendall,random,8,2,0.7857142857142856,0.005505952380952381
aggregate,aggregate,WildBench Creative,wildbench_240829.csv,kendall,random,8,3,0.7857142857142856,0.005505952380952381
aggregate,aggregate,WildBench Creative,wildbench_240829.csv,kendall,random,8,4,0.6428571428571428,0.03115079365079365
aggregate,aggregate,WildBench Code Debugging,wildbench_240829.csv,kendall,random,8,0,0.9999999999999998,4.96031746031746e-05
aggregate,aggregate,WildBench Code Debugging,wildbench_240829.csv,kendall,random,8,1,0.9999999999999998,4.96031746031746e-05
aggregate,aggregate,WildBench Code Debugging,wildbench_240829.csv,kendall,random,8,2,0.7857142857142856,0.005505952380952381
aggregate,aggregate,WildBench Code Debugging,wildbench_240829.csv,kendall,random,8,3,0.9285714285714285,0.0003968253968253968
aggregate,aggregate,WildBench Code Debugging,wildbench_240829.csv,kendall,random,8,4,0.9999999999999998,4.96031746031746e-05
aggregate,aggregate,WildBench Math & Data,wildbench_240829.csv,kendall,random,8,0,0.9999999999999998,4.96031746031746e-05
aggregate,aggregate,WildBench Math & Data,wildbench_240829.csv,kendall,random,8,1,0.9999999999999998,4.96031746031746e-05
aggregate,aggregate,WildBench Math & Data,wildbench_240829.csv,kendall,random,8,2,0.8571428571428571,0.001736111111111111
aggregate,aggregate,WildBench Math & Data,wildbench_240829.csv,kendall,random,8,3,0.9285714285714285,0.0003968253968253968
aggregate,aggregate,WildBench Math & Data,wildbench_240829.csv,kendall,random,8,4,0.9999999999999998,4.96031746031746e-05
aggregate,aggregate,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,8,0,0.9285714285714285,0.0003968253968253968
aggregate,aggregate,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,8,1,0.9999999999999998,4.96031746031746e-05
aggregate,aggregate,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,8,2,0.8571428571428571,0.001736111111111111
aggregate,aggregate,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,8,3,0.8571428571428571,0.001736111111111111
aggregate,aggregate,WildBench Reasoning & Planning,wildbench_240829.csv,kendall,random,8,4,0.9285714285714285,0.0003968253968253968
aggregate,aggregate,WildBench Score,wildbench_240829.csv,kendall,random,8,0,0.9999999999999998,4.96031746031746e-05
aggregate,aggregate,WildBench Score,wildbench_240829.csv,kendall,random,8,1,0.9999999999999998,4.96031746031746e-05
aggregate,aggregate,WildBench Score,wildbench_240829.csv,kendall,random,8,2,0.8571428571428571,0.001736111111111111
aggregate,aggregate,WildBench Score,wildbench_240829.csv,kendall,random,8,3,0.8571428571428571,0.001736111111111111
aggregate,aggregate,WildBench Score,wildbench_240829.csv,kendall,random,8,4,0.9999999999999998,4.96031746031746e-05
aggregate,aggregate,Arena Hard,arena_hard_240829.csv,kendall,random,8,0,0.9999999999999998,4.96031746031746e-05
aggregate,aggregate,Arena Hard,arena_hard_240829.csv,kendall,random,8,1,0.9999999999999998,4.96031746031746e-05
aggregate,aggregate,Arena Hard,arena_hard_240829.csv,kendall,random,8,2,0.9999999999999998,4.96031746031746e-05
aggregate,aggregate,Arena Hard,arena_hard_240829.csv,kendall,random,8,3,0.9999999999999998,4.96031746031746e-05
aggregate,aggregate,Arena Hard,arena_hard_240829.csv,kendall,random,8,4,0.9999999999999998,4.96031746031746e-05
aggregate,aggregate,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,0,0.14285714285714285,0.7195436507936508
aggregate,aggregate,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,1,0.4999999999999999,0.10868055555555556
aggregate,aggregate,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,2,0.6428571428571428,0.03115079365079365
aggregate,aggregate,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,3,0.6428571428571428,0.03115079365079365
aggregate,aggregate,HF OpenLLM v1,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,4,0.5714285714285714,0.06101190476190476
aggregate,aggregate,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,0,0.4999999999999999,0.10868055555555556
aggregate,aggregate,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,1,0.42857142857142855,0.17886904761904762
aggregate,aggregate,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,2,0.7857142857142856,0.005505952380952381
aggregate,aggregate,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,3,0.5714285714285714,0.06101190476190476
aggregate,aggregate,HFv1 ARC,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,4,0.3571428571428571,0.27509920634920637
aggregate,aggregate,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,0,0.0,1.0
aggregate,aggregate,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,1,0.5714285714285714,0.06101190476190476
aggregate,aggregate,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,2,0.5714285714285714,0.06101190476190476
aggregate,aggregate,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,3,0.6428571428571428,0.03115079365079365
aggregate,aggregate,HFv1 GSM8K,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,4,0.6428571428571428,0.03115079365079365
aggregate,aggregate,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,0,0.5714285714285714,0.06101190476190476
aggregate,aggregate,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,1,0.10910894511799618,0.7083840532183997
aggregate,aggregate,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,2,0.6182840223353117,0.0340492747686748
aggregate,aggregate,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,3,0.2857142857142857,0.39875992063492066
aggregate,aggregate,HFv1 HellaSwag,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,4,0.40006613209931935,0.17023995462900499
aggregate,aggregate,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,0,0.5714285714285714,0.06101190476190476
aggregate,aggregate,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,1,0.7857142857142856,0.005505952380952381
aggregate,aggregate,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,2,0.7857142857142856,0.005505952380952381
aggregate,aggregate,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,3,0.9285714285714285,0.0003968253968253968
aggregate,aggregate,HFv1 MMLU,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,4,0.7857142857142856,0.005505952380952381
aggregate,aggregate,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,0,0.4999999999999999,0.10868055555555556
aggregate,aggregate,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,1,0.2857142857142857,0.39875992063492066
aggregate,aggregate,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,2,0.6428571428571428,0.03115079365079365
aggregate,aggregate,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,3,0.42857142857142855,0.17886904761904762
aggregate,aggregate,HFv1 TruthfulQA,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,4,0.3571428571428571,0.27509920634920637
aggregate,aggregate,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,0,0.42857142857142855,0.17886904761904762
aggregate,aggregate,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,1,0.2857142857142857,0.39875992063492066
aggregate,aggregate,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,2,0.6182840223353117,0.0340492747686748
aggregate,aggregate,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,3,0.42857142857142855,0.17886904761904762
aggregate,aggregate,HFv1 Winogrande,hf_open_llm_v1_240829_frozen.csv,kendall,random,8,4,0.2857142857142857,0.39875992063492066
aggregate,aggregate,BFCL,bfcl_240906.csv,kendall,random,8,0,0.21428571428571427,0.5484126984126985
aggregate,aggregate,BFCL,bfcl_240906.csv,kendall,random,8,1,0.14285714285714285,0.7195436507936508
aggregate,aggregate,BFCL,bfcl_240906.csv,kendall,random,8,2,0.42857142857142855,0.17886904761904762
aggregate,aggregate,BFCL,bfcl_240906.csv,kendall,random,8,3,0.4999999999999999,0.10868055555555556
aggregate,aggregate,BFCL,bfcl_240906.csv,kendall,random,8,4,0.3571428571428571,0.27509920634920637
aggregate,aggregate,BIGGEN,biggen_240829.csv,kendall,random,8,0,0.7142857142857142,0.014136904761904762
aggregate,aggregate,BIGGEN,biggen_240829.csv,kendall,random,8,1,0.7857142857142856,0.005505952380952381
aggregate,aggregate,BIGGEN,biggen_240829.csv,kendall,random,8,2,0.7857142857142856,0.005505952380952381
aggregate,aggregate,BIGGEN,biggen_240829.csv,kendall,random,8,3,0.7142857142857142,0.014136904761904762
aggregate,aggregate,BIGGEN,biggen_240829.csv,kendall,random,8,4,0.7142857142857142,0.014136904761904762
aggregate,aggregate,BIGGEN Grounding,biggen_240829.csv,kendall,random,8,0,0.6428571428571428,0.03115079365079365
aggregate,aggregate,BIGGEN Grounding,biggen_240829.csv,kendall,random,8,1,0.8571428571428571,0.001736111111111111
aggregate,aggregate,BIGGEN Grounding,biggen_240829.csv,kendall,random,8,2,0.7142857142857142,0.014136904761904762
aggregate,aggregate,BIGGEN Grounding,biggen_240829.csv,kendall,random,8,3,0.7857142857142856,0.005505952380952381
aggregate,aggregate,BIGGEN Grounding,biggen_240829.csv,kendall,random,8,4,0.6428571428571428,0.03115079365079365
aggregate,aggregate,BIGGEN Instruction Following,biggen_240829.csv,kendall,random,8,0,0.40006613209931935,0.17023995462900499
aggregate,aggregate,BIGGEN Instruction Following,biggen_240829.csv,kendall,random,8,1,0.6910233190806425,0.017844011512848347
aggregate,aggregate,BIGGEN Instruction Following,biggen_240829.csv,kendall,random,8,2,0.7142857142857142,0.014136904761904762
aggregate,aggregate,BIGGEN Instruction Following,biggen_240829.csv,kendall,random,8,3,0.7142857142857142,0.014136904761904762
aggregate,aggregate,BIGGEN Instruction Following,biggen_240829.csv,kendall,random,8,4,0.47280542884465016,0.10506382347888965
aggregate,aggregate,BIGGEN Planning,biggen_240829.csv,kendall,random,8,0,0.47280542884465016,0.10506382347888965
aggregate,aggregate,BIGGEN Planning,biggen_240829.csv,kendall,random,8,1,0.42857142857142855,0.17886904761904762
aggregate,aggregate,BIGGEN Planning,biggen_240829.csv,kendall,random,8,2,0.7637626158259734,0.008839740160738534
aggregate,aggregate,BIGGEN Planning,biggen_240829.csv,kendall,random,8,3,0.5714285714285714,0.06101190476190476
aggregate,aggregate,BIGGEN Planning,biggen_240829.csv,kendall,random,8,4,0.10910894511799618,0.7083840532183997
aggregate,aggregate,BIGGEN Reasoning,biggen_240829.csv,kendall,random,8,0,0.8571428571428571,0.001736111111111111
aggregate,aggregate,BIGGEN Reasoning,biggen_240829.csv,kendall,random,8,1,0.9285714285714285,0.0003968253968253968
aggregate,aggregate,BIGGEN Reasoning,biggen_240829.csv,kendall,random,8,2,0.9999999999999998,4.96031746031746e-05
aggregate,aggregate,BIGGEN Reasoning,biggen_240829.csv,kendall,random,8,3,0.5714285714285714,0.06101190476190476
aggregate,aggregate,BIGGEN Reasoning,biggen_240829.csv,kendall,random,8,4,0.8571428571428571,0.001736111111111111
aggregate,aggregate,BIGGEN Refinement,biggen_240829.csv,kendall,random,8,0,0.7857142857142856,0.005505952380952381
aggregate,aggregate,BIGGEN Refinement,biggen_240829.csv,kendall,random,8,1,0.7637626158259734,0.008839740160738534
aggregate,aggregate,BIGGEN Refinement,biggen_240829.csv,kendall,random,8,2,0.9285714285714285,0.0003968253968253968
aggregate,aggregate,BIGGEN Refinement,biggen_240829.csv,kendall,random,8,3,0.6428571428571428,0.03115079365079365
aggregate,aggregate,BIGGEN Refinement,biggen_240829.csv,kendall,random,8,4,0.7637626158259734,0.008839740160738534
aggregate,aggregate,BIGGEN Safety,biggen_240829.csv,kendall,random,8,0,-0.2857142857142857,0.39875992063492066
aggregate,aggregate,BIGGEN Safety,biggen_240829.csv,kendall,random,8,1,0.2545875386086578,0.38281014365989596
aggregate,aggregate,BIGGEN Safety,biggen_240829.csv,kendall,random,8,2,0.6910233190806425,0.017844011512848347
aggregate,aggregate,BIGGEN Safety,biggen_240829.csv,kendall,random,8,3,0.10910894511799618,0.7083840532183997
aggregate,aggregate,BIGGEN Safety,biggen_240829.csv,kendall,random,8,4,0.07142857142857142,0.9048611111111111
aggregate,aggregate,BIGGEN Theory of Mind,biggen_240829.csv,kendall,random,8,0,0.4999999999999999,0.10868055555555556
aggregate,aggregate,BIGGEN Theory of Mind,biggen_240829.csv,kendall,random,8,1,0.6428571428571428,0.03115079365079365
aggregate,aggregate,BIGGEN Theory of Mind,biggen_240829.csv,kendall,random,8,2,0.836501912571304,0.004136737098676645
aggregate,aggregate,BIGGEN Theory of Mind,biggen_240829.csv,kendall,random,8,3,0.5669467095138409,0.05611472402809984
aggregate,aggregate,BIGGEN Theory of Mind,biggen_240829.csv,kendall,random,8,4,0.6182840223353117,0.0340492747686748
aggregate,aggregate,BIGGEN Tool Usage,biggen_240829.csv,kendall,random,8,0,0.7142857142857142,0.014136904761904762
aggregate,aggregate,BIGGEN Tool Usage,biggen_240829.csv,kendall,random,8,1,0.4999999999999999,0.10868055555555556
aggregate,aggregate,BIGGEN Tool Usage,biggen_240829.csv,kendall,random,8,2,0.5714285714285714,0.06101190476190476
aggregate,aggregate,BIGGEN Tool Usage,biggen_240829.csv,kendall,random,8,3,0.6428571428571428,0.03115079365079365
aggregate,aggregate,BIGGEN Tool Usage,biggen_240829.csv,kendall,random,8,4,0.42857142857142855,0.17886904761904762
aggregate,aggregate,BIGGEN Multilingual,biggen_240829.csv,kendall,random,8,0,0.7142857142857142,0.014136904761904762
aggregate,aggregate,BIGGEN Multilingual,biggen_240829.csv,kendall,random,8,1,0.8571428571428571,0.001736111111111111
aggregate,aggregate,BIGGEN Multilingual,biggen_240829.csv,kendall,random,8,2,0.42857142857142855,0.17886904761904762
aggregate,aggregate,BIGGEN Multilingual,biggen_240829.csv,kendall,random,8,3,0.6428571428571428,0.03115079365079365
aggregate,aggregate,BIGGEN Multilingual,biggen_240829.csv,kendall,random,8,4,0.8571428571428571,0.001736111111111111
aggregate,aggregate,LiveBench 240624,livebench_240701.csv,kendall,random,8,0,0.7142857142857142,0.014136904761904762
aggregate,aggregate,LiveBench 240624,livebench_240701.csv,kendall,random,8,1,0.9999999999999998,4.96031746031746e-05
aggregate,aggregate,LiveBench 240624,livebench_240701.csv,kendall,random,8,2,0.8571428571428571,0.001736111111111111
aggregate,aggregate,LiveBench 240624,livebench_240701.csv,kendall,random,8,3,0.8571428571428571,0.001736111111111111
aggregate,aggregate,LiveBench 240624,livebench_240701.csv,kendall,random,8,4,0.7857142857142856,0.005505952380952381
aggregate,aggregate,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,8,0,0.7412493166611012,0.011966745157436277
aggregate,aggregate,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,8,1,0.8571428571428571,0.001736111111111111
aggregate,aggregate,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,8,2,0.7637626158259734,0.008839740160738534
aggregate,aggregate,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,8,3,0.7142857142857142,0.014136904761904762
aggregate,aggregate,LiveBench Reasoning Average,livebench_240701.csv,kendall,random,8,4,0.8571428571428571,0.001736111111111111
aggregate,aggregate,LiveBench Coding Average,livebench_240701.csv,kendall,random,8,0,0.6428571428571428,0.03115079365079365
aggregate,aggregate,LiveBench Coding Average,livebench_240701.csv,kendall,random,8,1,0.9285714285714285,0.0003968253968253968
aggregate,aggregate,LiveBench Coding Average,livebench_240701.csv,kendall,random,8,2,0.7857142857142856,0.005505952380952381
aggregate,aggregate,LiveBench Coding Average,livebench_240701.csv,kendall,random,8,3,0.9999999999999998,4.96031746031746e-05
aggregate,aggregate,LiveBench Coding Average,livebench_240701.csv,kendall,random,8,4,0.7637626158259734,0.008839740160738534
aggregate,aggregate,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,8,0,0.7142857142857142,0.014136904761904762
aggregate,aggregate,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,8,1,0.9999999999999998,4.96031746031746e-05
aggregate,aggregate,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,8,2,0.7142857142857142,0.014136904761904762
aggregate,aggregate,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,8,3,0.8571428571428571,0.001736111111111111
aggregate,aggregate,LiveBench Mathematics Average,livebench_240701.csv,kendall,random,8,4,0.8571428571428571,0.001736111111111111
aggregate,aggregate,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,8,0,0.4999999999999999,0.10868055555555556
aggregate,aggregate,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,8,1,0.8571428571428571,0.001736111111111111
aggregate,aggregate,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,8,2,0.7142857142857142,0.014136904761904762
aggregate,aggregate,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,8,3,0.7857142857142856,0.005505952380952381
aggregate,aggregate,LiveBench Data Analysis Average,livebench_240701.csv,kendall,random,8,4,0.6428571428571428,0.03115079365079365
aggregate,aggregate,LiveBench Language Average,livebench_240701.csv,kendall,random,8,0,0.6428571428571428,0.03115079365079365
aggregate,aggregate,LiveBench Language Average,livebench_240701.csv,kendall,random,8,1,0.9999999999999998,4.96031746031746e-05
aggregate,aggregate,LiveBench Language Average,livebench_240701.csv,kendall,random,8,2,0.7142857142857142,0.014136904761904762
aggregate,aggregate,LiveBench Language Average,livebench_240701.csv,kendall,random,8,3,0.7857142857142856,0.005505952380952381
aggregate,aggregate,LiveBench Language Average,livebench_240701.csv,kendall,random,8,4,0.8571428571428571,0.001736111111111111
aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,8,0,0.5714285714285714,0.06101190476190476
aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,8,1,0.8571428571428571,0.001736111111111111
aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,8,2,0.7857142857142856,0.005505952380952381
aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,8,3,0.5714285714285714,0.06101190476190476
aggregate,aggregate,LiveBench Instruction Following Average,livebench_240701.csv,kendall,random,8,4,0.7857142857142856,0.005505952380952381