---
base_model:
- RekaAI/reka-flash-3
---
vllm (pretrained=/root/autodl-tmp/reka-flash-3,add_bos_token=true,max_model_len=4096,dtype=bfloat16), gen_kwargs: (None), limit: 250.0, num_fewshot: 5, batch_size: auto
|Tasks|Version|     Filter     |n-shot|  Metric   |   |Value|   |Stderr|
|-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
|gsm8k|      3|flexible-extract|     5|exact_match|↑  |0.720|±  |0.0285|
|     |       |strict-match    |     5|exact_match|↑  |0.676|±  |0.0297|

vllm (pretrained=/root/autodl-tmp/reka-flash-3,add_bos_token=true,max_model_len=4096,dtype=bfloat16), gen_kwargs: (None), limit: 500.0, num_fewshot: 5, batch_size: auto
|Tasks|Version|     Filter     |n-shot|  Metric   |   |Value|   |Stderr|
|-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
|gsm8k|      3|flexible-extract|     5|exact_match|↑  |0.724|±  |0.0200|
|     |       |strict-match    |     5|exact_match|↑  |0.684|±  |0.0208|

vllm (pretrained=/root/autodl-tmp/reka-flash-3,add_bos_token=true,max_model_len=4096,dtype=bfloat16,max_num_seqs=3), gen_kwargs: (None), limit: 15.0, num_fewshot: None, batch_size: 1
|      Groups      |Version|Filter|n-shot|Metric|   |Value |   |Stderr|
|------------------|------:|------|------|------|---|-----:|---|-----:|
|mmlu              |      2|none  |      |acc   |↑  |0.6480|±  |0.0158|
| - humanities     |      2|none  |      |acc   |↑  |0.6615|±  |0.0328|
| - other          |      2|none  |      |acc   |↑  |0.6667|±  |0.0328|
| - social sciences|      2|none  |      |acc   |↑  |0.7167|±  |0.0334|
| - stem           |      2|none  |      |acc   |↑  |0.5825|±  |0.0284|


vllm (pretrained=/root/autodl-tmp/84-512,add_bos_token=true,max_model_len=4096,dtype=bfloat16), gen_kwargs: (None), limit: 250.0, num_fewshot: 5, batch_size: auto
|Tasks|Version|     Filter     |n-shot|  Metric   |   |Value|   |Stderr|
|-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
|gsm8k|      3|flexible-extract|     5|exact_match|↑  |0.700|±  |0.0290|
|     |       |strict-match    |     5|exact_match|↑  |0.648|±  |0.0303|

vllm (pretrained=/root/autodl-tmp/84-512,add_bos_token=true,max_model_len=4096,dtype=bfloat16), gen_kwargs: (None), limit: 500.0, num_fewshot: 5, batch_size: auto
|Tasks|Version|     Filter     |n-shot|  Metric   |   |Value|   |Stderr|
|-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
|gsm8k|      3|flexible-extract|     5|exact_match|↑  |0.692|±  |0.0207|
|     |       |strict-match    |     5|exact_match|↑  |0.648|±  |0.0214|

vllm (pretrained=/root/autodl-tmp/84-512,add_bos_token=true,max_model_len=4096,dtype=bfloat16,max_num_seqs=3), gen_kwargs: (None), limit: 15.0, num_fewshot: None, batch_size: 1
|      Groups      |Version|Filter|n-shot|Metric|   |Value |   |Stderr|
|------------------|------:|------|------|------|---|-----:|---|-----:|
|mmlu              |      2|none  |      |acc   |↑  |0.6515|±  |0.0159|
| - humanities     |      2|none  |      |acc   |↑  |0.6718|±  |0.0325|
| - other          |      2|none  |      |acc   |↑  |0.6718|±  |0.0328|
| - social sciences|      2|none  |      |acc   |↑  |0.7056|±  |0.0341|
| - stem           |      2|none  |      |acc   |↑  |0.5895|±  |0.0286|


vllm (pretrained=/root/autodl-tmp/848-128,add_bos_token=true,max_model_len=4096,dtype=bfloat16), gen_kwargs: (None), limit: 250.0, num_fewshot: 5, batch_size: auto
|Tasks|Version|     Filter     |n-shot|  Metric   |   |Value|   |Stderr|
|-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
|gsm8k|      3|flexible-extract|     5|exact_match|↑  |0.692|±  |0.0293|
|     |       |strict-match    |     5|exact_match|↑  |0.660|±  |0.0300|

vllm (pretrained=/root/autodl-tmp/848-128,add_bos_token=true,max_model_len=4096,dtype=bfloat16), gen_kwargs: (None), limit: 500.0, num_fewshot: 5, batch_size: auto
|Tasks|Version|     Filter     |n-shot|  Metric   |   |Value|   |Stderr|
|-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
|gsm8k|      3|flexible-extract|     5|exact_match|↑  |0.724|±  | 0.020|
|     |       |strict-match    |     5|exact_match|↑  |0.674|±  | 0.021|

vllm (pretrained=/root/autodl-tmp/848-128,add_bos_token=true,max_model_len=4096,dtype=bfloat16,max_num_seqs=3), gen_kwargs: (None), limit: 15.0, num_fewshot: None, batch_size: 1
|      Groups      |Version|Filter|n-shot|Metric|   |Value |   |Stderr|
|------------------|------:|------|------|------|---|-----:|---|-----:|
|mmlu              |      2|none  |      |acc   |↑  |0.6398|±  |0.0159|
| - humanities     |      2|none  |      |acc   |↑  |0.6513|±  |0.0333|
| - other          |      2|none  |      |acc   |↑  |0.6564|±  |0.0330|
| - social sciences|      2|none  |      |acc   |↑  |0.7222|±  |0.0333|
| - stem           |      2|none  |      |acc   |↑  |0.5684|±  |0.0284|


vllm (pretrained=/root/autodl-tmp/8485-512,add_bos_token=true,max_model_len=4096,dtype=bfloat16), gen_kwargs: (None), limit: 250.0, num_fewshot: 5, batch_size: auto
|Tasks|Version|     Filter     |n-shot|  Metric   |   |Value|   |Stderr|
|-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
|gsm8k|      3|flexible-extract|     5|exact_match|↑  |0.732|±  |0.0281|
|     |       |strict-match    |     5|exact_match|↑  |0.696|±  |0.0292|

vllm (pretrained=/root/autodl-tmp/8485-512,add_bos_token=true,max_model_len=4096,dtype=bfloat16), gen_kwargs: (None), limit: 500.0, num_fewshot: 5, batch_size: auto
|Tasks|Version|     Filter     |n-shot|  Metric   |   |Value|   |Stderr|
|-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
|gsm8k|      3|flexible-extract|     5|exact_match|↑  |0.720|±  |0.0201|
|     |       |strict-match    |     5|exact_match|↑  |0.692|±  |0.0207|

vllm (pretrained=/root/autodl-tmp/8485-512,add_bos_token=true,max_model_len=4096,dtype=bfloat16,max_num_seqs=3), gen_kwargs: (None), limit: 15.0, num_fewshot: None, batch_size: 1
|      Groups      |Version|Filter|n-shot|Metric|   |Value |   |Stderr|
|------------------|------:|------|------|------|---|-----:|---|-----:|
|mmlu              |      2|none  |      |acc   |↑  |0.6550|±  |0.0158|
| - humanities     |      2|none  |      |acc   |↑  |0.6872|±  |0.0323|
| - other          |      2|none  |      |acc   |↑  |0.6769|±  |0.0327|
| - social sciences|      2|none  |      |acc   |↑  |0.7056|±  |0.0341|
| - stem           |      2|none  |      |acc   |↑  |0.5860|±  |0.0284|


vllm (pretrained=/root/autodl-tmp/8485-128,add_bos_token=true,max_model_len=4096,dtype=bfloat16), gen_kwargs: (None), limit: 250.0, num_fewshot: 5, batch_size: auto
|Tasks|Version|     Filter     |n-shot|  Metric   |   |Value|   |Stderr|
|-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
|gsm8k|      3|flexible-extract|     5|exact_match|↑  | 0.74|±  |0.0278|
|     |       |strict-match    |     5|exact_match|↑  | 0.68|±  |0.0296|

vllm (pretrained=/root/autodl-tmp/8485-128,add_bos_token=true,max_model_len=4096,dtype=bfloat16), gen_kwargs: (None), limit: 500.0, num_fewshot: 5, batch_size: auto
|Tasks|Version|     Filter     |n-shot|  Metric   |   |Value|   |Stderr|
|-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
|gsm8k|      3|flexible-extract|     5|exact_match|↑  |0.714|±  |0.0202|
|     |       |strict-match    |     5|exact_match|↑  |0.676|±  |0.0210|

vllm (pretrained=/root/autodl-tmp/8485-128,add_bos_token=true,max_model_len=4096,dtype=bfloat16,max_num_seqs=3), gen_kwargs: (None), limit: 15.0, num_fewshot: None, batch_size: 1
|      Groups      |Version|Filter|n-shot|Metric|   |Value |   |Stderr|
|------------------|------:|------|------|------|---|-----:|---|-----:|
|mmlu              |      2|none  |      |acc   |↑  |0.6433|±  |0.0160|
| - humanities     |      2|none  |      |acc   |↑  |0.6513|±  |0.0337|
| - other          |      2|none  |      |acc   |↑  |0.6615|±  |0.0332|
| - social sciences|      2|none  |      |acc   |↑  |0.7111|±  |0.0338|
| - stem           |      2|none  |      |acc   |↑  |0.5825|±  |0.0284|


vllm (pretrained=/root/autodl-tmp/85-128,add_bos_token=true,max_model_len=4096,dtype=bfloat16), gen_kwargs: (None), limit: 250.0, num_fewshot: 5, batch_size: auto
|Tasks|Version|     Filter     |n-shot|  Metric   |   |Value|   |Stderr|
|-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
|gsm8k|      3|flexible-extract|     5|exact_match|↑  |0.696|±  |0.0292|
|     |       |strict-match    |     5|exact_match|↑  |0.648|±  |0.0303|

vllm (pretrained=/root/autodl-tmp/85-128,add_bos_token=true,max_model_len=4096,dtype=bfloat16), gen_kwargs: (None), limit: 500.0, num_fewshot: 5, batch_size: auto
|Tasks|Version|     Filter     |n-shot|  Metric   |   |Value|   |Stderr|
|-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
|gsm8k|      3|flexible-extract|     5|exact_match|↑  |0.708|±  |0.0204|
|     |       |strict-match    |     5|exact_match|↑  |0.660|±  |0.0212|

vllm (pretrained=/root/autodl-tmp/85-128,add_bos_token=true,max_model_len=4096,dtype=bfloat16,max_num_seqs=3), gen_kwargs: (None), limit: 15.0, num_fewshot: None, batch_size: 1
|      Groups      |Version|Filter|n-shot|Metric|   |Value |   |Stderr|
|------------------|------:|------|------|------|---|-----:|---|-----:|
|mmlu              |      2|none  |      |acc   |↑  |0.6526|±  |0.0158|
| - humanities     |      2|none  |      |acc   |↑  |0.6615|±  |0.0331|
| - other          |      2|none  |      |acc   |↑  |0.6769|±  |0.0325|
| - social sciences|      2|none  |      |acc   |↑  |0.7389|±  |0.0327|
| - stem           |      2|none  |      |acc   |↑  |0.5754|±  |0.0287|


vllm (pretrained=/root/autodl-tmp/85-512,add_bos_token=true,max_model_len=4096,dtype=bfloat16), gen_kwargs: (None), limit: 250.0, num_fewshot: 5, batch_size: auto
|Tasks|Version|     Filter     |n-shot|  Metric   |   |Value|   |Stderr|
|-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
|gsm8k|      3|flexible-extract|     5|exact_match|↑  |0.708|±  |0.0288|
|     |       |strict-match    |     5|exact_match|↑  |0.648|±  |0.0303|

vllm (pretrained=/root/autodl-tmp/85-512,add_bos_token=true,max_model_len=4096,dtype=bfloat16), gen_kwargs: (None), limit: 500.0, num_fewshot: 5, batch_size: auto
|Tasks|Version|     Filter     |n-shot|  Metric   |   |Value|   |Stderr|
|-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
|gsm8k|      3|flexible-extract|     5|exact_match|↑  |0.720|±  |0.0201|
|     |       |strict-match    |     5|exact_match|↑  |0.658|±  |0.0212|

vllm (pretrained=/root/autodl-tmp/85-512,add_bos_token=true,max_model_len=4096,dtype=bfloat16,max_num_seqs=3), gen_kwargs: (None), limit: 15.0, num_fewshot: None, batch_size: 1
|      Groups      |Version|Filter|n-shot|Metric|   |Value |   |Stderr|
|------------------|------:|------|------|------|---|-----:|---|-----:|
|mmlu              |      2|none  |      |acc   |↑  |0.6550|±  |0.0158|
| - humanities     |      2|none  |      |acc   |↑  |0.6769|±  |0.0324|
| - other          |      2|none  |      |acc   |↑  |0.6667|±  |0.0331|
| - social sciences|      2|none  |      |acc   |↑  |0.7278|±  |0.0329|
| - stem           |      2|none  |      |acc   |↑  |0.5860|±  |0.0284|


vllm (pretrained=/root/autodl-tmp/86-128,add_bos_token=true,max_model_len=4096,dtype=bfloat16), gen_kwargs: (None), limit: 250.0, num_fewshot: 5, batch_size: auto
|Tasks|Version|     Filter     |n-shot|  Metric   |   |Value|   |Stderr|
|-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
|gsm8k|      3|flexible-extract|     5|exact_match|↑  |0.696|±  |0.0292|
|     |       |strict-match    |     5|exact_match|↑  |0.636|±  |0.0305|

vllm (pretrained=/root/autodl-tmp/86-128,add_bos_token=true,max_model_len=4096,dtype=bfloat16), gen_kwargs: (None), limit: 500.0, num_fewshot: 5, batch_size: auto
|Tasks|Version|     Filter     |n-shot|  Metric   |   |Value|   |Stderr|
|-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
|gsm8k|      3|flexible-extract|     5|exact_match|↑  |0.690|±  |0.0207|
|     |       |strict-match    |     5|exact_match|↑  |0.648|±  |0.0214|

vllm (pretrained=/root/autodl-tmp/86-128,add_bos_token=true,max_model_len=4096,dtype=bfloat16,max_num_seqs=3), gen_kwargs: (None), limit: 15.0, num_fewshot: None, batch_size: 1
|      Groups      |Version|Filter|n-shot|Metric|   |Value |   |Stderr|
|------------------|------:|------|------|------|---|-----:|---|-----:|
|mmlu              |      2|none  |      |acc   |↑  |0.6398|±  |0.0160|
| - humanities     |      2|none  |      |acc   |↑  |0.6410|±  |0.0336|
| - other          |      2|none  |      |acc   |↑  |0.6564|±  |0.0332|
| - social sciences|      2|none  |      |acc   |↑  |0.7278|±  |0.0333|
| - stem           |      2|none  |      |acc   |↑  |0.5719|±  |0.0284|


vllm (pretrained=/root/autodl-tmp/86-512,add_bos_token=true,max_model_len=4096,dtype=bfloat16), gen_kwargs: (None), limit: 250.0, num_fewshot: 5, batch_size: auto
|Tasks|Version|     Filter     |n-shot|  Metric   |   |Value|   |Stderr|
|-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
|gsm8k|      3|flexible-extract|     5|exact_match|↑  |0.688|±  |0.0294|
|     |       |strict-match    |     5|exact_match|↑  |0.640|±  |0.0304|

vllm (pretrained=/root/autodl-tmp/86-512,add_bos_token=true,max_model_len=4096,dtype=bfloat16), gen_kwargs: (None), limit: 500.0, num_fewshot: 5, batch_size: auto
|Tasks|Version|     Filter     |n-shot|  Metric   |   |Value|   |Stderr|
|-----|------:|----------------|-----:|-----------|---|----:|---|-----:|
|gsm8k|      3|flexible-extract|     5|exact_match|↑  |0.706|±  |0.0204|
|     |       |strict-match    |     5|exact_match|↑  |0.660|±  |0.0212|

|      Groups      |Version|Filter|n-shot|Metric|   |Value |   |Stderr|
|------------------|------:|------|------|------|---|-----:|---|-----:|
|mmlu              |      2|none  |      |acc   |↑  |0.6526|±  |0.0158|
| - humanities     |      2|none  |      |acc   |↑  |0.6821|±  |0.0327|
| - other          |      2|none  |      |acc   |↑  |0.6615|±  |0.0331|
| - social sciences|      2|none  |      |acc   |↑  |0.7278|±  |0.0329|
| - stem           |      2|none  |      |acc   |↑  |0.5789|±  |0.0284|