NousResearch/eval-Cogito-v2-preview-405B-reasoning download history

NousResearch/eval-Cogito-v2-preview-405B-reasoning is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 301 times (30 in the last 7 days), and 1,620 times in total. It ranks #48,977 among datasets by monthly downloads.

cogito-405b-thinking Evaluation Results Summary Benchmark Score Metric Samples Overlong rate aime24 0.408 math_pass@1:64_samples 64 20.3% aime25 0.327 math_pass@1:64_samples 64 15.5% arenahard 0.910 eval/overall_winrate 500 0.0% bbh_generative 0.893 extractive_

Open NousResearch/eval-Cogito-v2-preview-405B-reasoning on Hugging Face