Spaces:
Running
Running
model,score | |
gpt_4o_2024_05_13,1.0 | |
gpt_4_0613,0.971830985915493 | |
claude_3.5_sonnet_20240620,0.971830985915493 | |
gpt_4_turbo_2024_04_09,0.9577464788732394 | |
llama3.1_instruct_turbo_405b,0.9436619718309859 | |
llama3.1_instruct_turbo_70b,0.9295774647887324 | |
llama3_70b,0.9154929577464789 | |
qwen2_instruct_72b,0.9014084507042254 | |
mistral_large_2_2407,0.8873239436619719 | |
gemini_1.5_pro_001,0.8732394366197183 | |
gpt_4o_mini_2024_07_18,0.8591549295774648 | |
mixtral_8x22b,0.8450704225352113 | |
gpt_4_turbo_1106_preview,0.8309859154929577 | |
palmyra_x_v3_72b,0.8169014084507042 | |
gemma_2_instruct_27b,0.8028169014084507 | |
gemini_1.5_flash_001,0.7887323943661971 | |
claude_3_opus_20240229,0.7746478873239436 | |
palm_2_unicorn,0.7605633802816901 | |
qwen1.5_72b,0.7464788732394366 | |
palmyra_x_v2_33b,0.7323943661971831 | |
gemma_2_instruct_9b,0.7183098591549296 | |
yi_34b,0.704225352112676 | |
qwen1.5_chat_110b,0.6901408450704225 | |
qwen1.5_32b,0.676056338028169 | |
claude_v1.3,0.6619718309859155 | |
palm_2_bison,0.647887323943662 | |
mixtral_8x7b_32k_seqlen,0.6338028169014085 | |
phi_3_14b,0.6197183098591549 | |
claude_2.0,0.6056338028169014 | |
deepseek_llm_chat_67b,0.5915492957746479 | |
phi_3_7b,0.5774647887323944 | |
llama_2_70b,0.5633802816901409 | |
yi_large_preview,0.5492957746478874 | |
command_r_plus,0.5352112676056338 | |
gpt_3.5_text_davinci_003,0.5070422535211268 | |
claude_2.1,0.5070422535211268 | |
qwen1.5_14b,0.49295774647887325 | |
gemini_1.0_pro_002,0.4788732394366197 | |
claude_instant_1.2,0.4647887323943662 | |
llama3_8b,0.4507042253521127 | |
gpt_3.5_turbo_0613,0.4225352112676056 | |
claude_3_sonnet_20240229,0.4225352112676056 | |
mistral_nemo_2402,0.4084507042253521 | |
arctic_instruct,0.39436619718309857 | |
gpt_3.5_text_davinci_002,0.36619718309859156 | |
gemma_7b,0.36619718309859156 | |
llama_65b,0.352112676056338 | |
mistral_large_2402,0.3380281690140845 | |
command,0.323943661971831 | |
command_r,0.30985915492957744 | |
llama3.1_instruct_turbo_8b,0.29577464788732394 | |
mistral_small_2402,0.28169014084507044 | |
dbrx_instructruct,0.2676056338028169 | |
jamba_instruct,0.2535211267605634 | |
mistral_v0.1_7b,0.23943661971830985 | |
mistral_medium_2312,0.22535211267605634 | |
qwen1.5_7b,0.2112676056338028 | |
claude_3_haiku_20240307,0.19718309859154928 | |
yi_6b,0.18309859154929578 | |
llama_2_13b,0.16901408450704225 | |
jurassic_2_jumbo_178b,0.15492957746478872 | |
falcon_40b,0.14084507042253522 | |
mistral_instruct_v0.3_7b,0.1267605633802817 | |
jurassic_2_grande_17b,0.11267605633802817 | |
phi_2,0.09859154929577464 | |
llama_2_7b,0.08450704225352113 | |
luminous_supreme_70b,0.07042253521126761 | |
command_light,0.056338028169014086 | |
luminous_extended_30b,0.04225352112676056 | |
falcon_7b,0.028169014084507043 | |
olmo_7b,0.014084507042253521 | |
luminous_base_13b,0.0 | |