List your company

Mathematical Reasoning on MATH (pass@1, pass@16)

85.7Pass@1TTRL
62.71668.68374.6580.617Sep 18, 2025

Evaluation results

MethodLinks
TTRLBase Model Size=8B, Training Dataset=MATH-5002025.0985.791.9
EVOL-RLBase Model Size=8B, Training Dataset=MATH-5002025.0984.795.1
EVOL-RLBase Model Size=8B, Training Dataset=MATH-TRAIN2025.0983.694.1
EVOL-RLBase Model Size=8B, Training Dataset=AIME242025.0983.194.2
TTRLBase Model Size=8B, Training Dataset=MATH-TRAIN2025.0981.191.1
EVOL-RLBase Model Size=4B, Training Dataset=MATH-TRAIN2025.098093.3
EVOL-RLBase Model Size=4B, Training Dataset=MATH-5002025.0979.893.8
EVOL-RLBase Model Size=4B, Training Dataset=AIME242025.0979.693.6
TTRLBase Model Size=4B, Training Dataset=MATH-5002025.0979.383.2
TTRLBase Model Size=8B, Training Dataset=AIME242025.0976.886.2
TTRLBase Model Size=4B, Training Dataset=MATH-TRAIN2025.0975.486.9
TTRLBase Model Size=4B, Training Dataset=AIME242025.0973.884.5
Qwen3-4B-BaseBase Model Size=4B, Training Dataset=-2025.0967.489.6
Qwen3-8B-BaseBase Model Size=8B, Training Dataset=-2025.0963.691.5