List your company

Mathematical Reasoning on GSM8K (Pass@1 Accuracy)

96.4GSM8K Pass@1 AccuracyClaude3.5-Sonnet
8688.791.494.1Feb 18, 2025

Evaluation results

MethodLinks
Claude3.5-SonnetDecoding=Greedy2025.0296.4
GPT-o1-miniDecoding=Greedy2025.0294.8
GPT-4oDecoding=Greedy2025.0292.9
Qwen2.5-Math-7B-S2R-ORLBackbone=Qwen2.5-Math-7B, Training Strategy=Outcome-level RL, Decoding=Greedy2025.0292.9
Llama-3.1-8B-S2R-ORLBackbone=Llama-3.1-8B, Training Strategy=Outcome-level RL, Decoding=Greedy2025.0287.3
Qwen2-7B-S2R-ORLBackbone=Qwen2-7B, Training Strategy=Outcome-level RL, Decoding=Greedy2025.0286.4