Math Reasoning Models

rStar2-Agent-14B

Qwen2.5-0.5B-GRPO-math-reasoning

REAL-Prover

DAPO-with-prompt-augmentation-step2820

Weak-Driven-Learning

DAPO-with-prompt-augmentation-step2720

DAPO-with-prompt-augmentation-step2480

VEHME

Qwen2.5-14B-ES-MATH

ANMOLGPT-4B-v0.5

Nebula-S-v1

Eklav-9B-Math

Eklav-8B-Math

Eklav-9B-Math-CotGen

Eklav-14B-Math-CotGen

Eklav-8B-Math-CotGen

R1-Distill-Qwen-1.5B-OPD-R1-7B-Step200

UniReason-Qwen3-14B-RL

Qwen3-1.7B-OPD-Qwen3-4B-Step200

WirelessMathLM-Qwen3-4B

Qwen3-1.7B-OPD-RL-Math-Step200

Qwen3-1.7B-GRPO-KL-math-reasoning

Qwen2.5-1.5B-RLOO-math-reasoning

Qwen2.5-1.5B-GRPO-math-reasoning

Qwen2.5-1.5B-DAPO-math-reasoning

Qwen2.5-1.5B-GRPO-KL-math-reasoning

Qwen2.5-1.5B-ReMax-math-reasoning

Qwen3-1.7B-RLOO-math-reasoning

Qwen2.5-0.5B-RLOO-math-reasoning

Qwen2.5-3B-GRPO-math-reasoning

Qwen2.5-0.5B-DAPO-math-reasoning

Qwen3-1.7B-DAPO-math-reasoning

Qwen2.5-0.5B-ReMax-math-reasoning

Qwen2.5-0.5B-GRPO-KL-math-reasoning

Qwen3-1.7B-ReMax-math-reasoning

Qwen2.5-3B-RLOO-math-reasoning

UniReason-Qwen3-14B-think-SFT

Qwen3-1.7B-GRPO-math-reasoning

Qwen2.5-3B-GRPO-KL-math-reasoning

Qwen2.5-3B-DAPO-math-reasoning

Fast-Math-R1-14B

Qwen2.5-3B-ReMax-math-reasoning