| dataset,version,metric,mode,internvl-chat-20b | |
| mmlu,-,naive_average,gen,46.35 | |
| mmlu_pro,-,-,-,- | |
| cmmlu,-,naive_average,gen,47.13 | |
| ceval,-,naive_average,gen,48.56 | |
| agieval,-,-,-,- | |
| GaokaoBench,-,weighted_average,gen,32.28 | |
| GPQA_extended,-,-,-,- | |
| GPQA_main,-,-,-,- | |
| GPQA_diamond,-,-,-,- | |
| ARC-c,-,-,-,- | |
| truthfulqa,-,-,-,- | |
| triviaqa,2121ce,score,gen,31.47 | |
| triviaqa_wiki_1shot,-,-,-,- | |
| nq,3dcea1,score,gen,13.21 | |
| C3,8c358f,accuracy,gen,76.88 | |
| race-high,9a54b6,accuracy,gen,72.56 | |
| flores_100,-,-,-,- | |
| winogrande,b36770,accuracy,gen,58.72 | |
| hellaswag,e42710,accuracy,gen,53.69 | |
| bbh,-,naive_average,gen,36.32 | |
| gsm8k,1d7fe4,accuracy,gen,40.71 | |
| math,393424,accuracy,gen,6.96 | |
| TheoremQA,6f0af8,score,gen,12.25 | |
| MathBench,-,-,-,- | |
| openai_humaneval,8e312c,humaneval_pass@1,gen,32.32 | |
| humaneval_plus,-,-,-,- | |
| humanevalx,-,-,-,- | |
| sanitized_mbpp,a447ff,score,gen,33.07 | |
| mbpp_plus,-,-,-,- | |
| mbpp_cn,6fb572,score,gen,23.40 | |
| leval,-,-,-,- | |
| leval_closed,-,-,-,- | |
| leval_open,-,-,-,- | |
| longbench,-,-,-,- | |
| longbench_single-document-qa,-,-,-,- | |
| longbench_multi-document-qa,-,-,-,- | |
| longbench_summarization,-,-,-,- | |
| longbench_few-shot-learning,-,-,-,- | |
| longbench_synthetic-tasks,-,-,-,- | |
| longbench_code-completion,-,-,-,- | |
| teval,-,-,-,- | |
| teval_zh,-,-,-,- | |
| IFEval,3321a3,Prompt-level-strict-accuracy,gen,19.78 | |
| IFEval,3321a3,Inst-level-strict-accuracy,gen,31.89 | |
| IFEval,3321a3,Prompt-level-loose-accuracy,gen,22.92 | |
| IFEval,3321a3,Inst-level-loose-accuracy,gen,35.13 | |