List your company

Math reasoning on OlympiadBench (Pass@1)

55.6Pass@1OpenThinker3-7B
31.99238.12144.2550.379May 20, 2025Jul 10, 2025Aug 31, 2025Oct 22, 2025Dec 12, 2025Feb 2, 2026Mar 26, 2026

Evaluation results

MethodLinks
OpenThinker3-7B2026.0355.6
AAPO-1.5BZero-shot=true, Number of parameters=1.5B2025.0553.3
GPG-1.5BZero-shot=true, Number of parameters=1.5B2025.0552.4
GRPO-1.5BZero-shot=true, Number of parameters=1.5B2025.0551.3
Sampled-token OPDmasking=true2026.0344.7
AAPO-7BZero-shot=true, Number of parameters=7B2025.0544.3
teacher top-K local support matchingmasking=false2026.0343.9
teacher top-K local support matchingmasking=true2026.0343.9
Sampled-token OPDmasking=false2026.0343.1
GPG-7BZero-shot=true, Number of parameters=7B2025.0542.4
Oat-Zero-7BZero-shot=true, Number of parameters=7B2025.0541
SimpleRL-Zero-7BZero-shot=true, Number of parameters=7B2025.0540.4
Eurus-2-7B-PRIMEZero-shot=true, Number of parameters=7B2025.0540.3
Qwen2.5-7B-It2026.0332.9