List your company

Science Reasoning on GPQA (FRS, pass@1 accuracy)

62.9FRS ScoreDS-R1-7B
29.6238.2646.955.54Apr 13, 2026

Evaluation results

MethodLinks
DS-R1-7BFiltering rate=10%, Decoding strategy=greedy2026.0462.9—
Phi-4-Reas.Filtering rate=10%, Decoding strategy=greedy2026.0462.3—
Qwen3-4BFiltering rate=10%, Decoding strategy=greedy2026.0458.8—
DS-R1-1.5BFiltering rate=10%, Decoding strategy=greedy2026.0456.6—
Qwen2.5-7BFiltering rate=10%, Decoding strategy=greedy2026.0455.1—
Qwen2.5-MathFiltering rate=10%, Decoding strategy=greedy2026.0454.6—
LLaMA-3.1-8BFiltering rate=10%, Decoding strategy=greedy2026.0450.5—
Phi-4Filtering rate=10%, Decoding strategy=greedy2026.0448.4—
Gemma-7BFiltering rate=10%, Decoding strategy=greedy2026.0430.9—