List your company

Mathematical Reasoning on AIME 2025 (Mean@64 accuracy)

51.2Mean@64 AccAgentic Proposing
42.77644.96347.1549.337Feb 3, 2026

Evaluation results

MethodLinks
Agentic Proposingtraining budget=10,000-trajectory, recipe=GRPO, backbone=Qwen3-4B-Instruct-25072026.0251.2
PromptCot 2.0training budget=10,000-trajectory, recipe=GRPO, backbone=Qwen3-4B-Instruct-25072026.0248.5
Deepmathtraining budget=10,000-trajectory, recipe=GRPO, backbone=Qwen3-4B-Instruct-25072026.0248.2
Polaristraining budget=10,000-trajectory, recipe=GRPO, backbone=Qwen3-4B-Instruct-25072026.0247.4
PromptCoTtraining budget=10,000-trajectory, recipe=GRPO, backbone=Qwen3-4B-Instruct-25072026.0247.3
MathSmithtraining budget=10,000-trajectory, recipe=GRPO, backbone=Qwen3-4B-Instruct-25072026.0247.1
Socratic-zerotraining budget=10,000-trajectory, recipe=GRPO, backbone=Qwen3-4B-Instruct-25072026.0246.9
Qwen3-4B-Instruct-2507mode=zero-shot2026.0246.7
OpenthoughtsS3training budget=10,000-trajectory, recipe=GRPO, backbone=Qwen3-4B-Instruct-25072026.0246.1
OpenR1mathtraining budget=10,000-trajectory, recipe=GRPO, backbone=Qwen3-4B-Instruct-25072026.0245.8
GPT-5.2-Hightraining budget=10,000-trajectory, recipe=GRPO, backbone=Qwen3-4B-Instruct-25072026.0245.8
Claude4.5-Opustraining budget=10,000-trajectory, recipe=GRPO, backbone=Qwen3-4B-Instruct-25072026.0245.7
DeepSeek-V3.2-Spetraining budget=10,000-trajectory, recipe=GRPO, backbone=Qwen3-4B-Instruct-25072026.0245.6
R-zerotraining budget=10,000-trajectory, recipe=GRPO, backbone=Qwen3-4B-Instruct-25072026.0244.3
Wizardmathtraining budget=10,000-trajectory, recipe=GRPO, backbone=Qwen3-4B-Instruct-25072026.0244
NuminaMathtraining budget=10,000-trajectory, recipe=GRPO, backbone=Qwen3-4B-Instruct-25072026.0243.9
Metamathtraining budget=10,000-trajectory, recipe=GRPO, backbone=Qwen3-4B-Instruct-25072026.0243.5
Qwen3-Maxtraining budget=10,000-trajectory, recipe=GRPO, backbone=Qwen3-4B-Instruct-25072026.0243.4
Gemini-3-Protraining budget=10,000-trajectory, recipe=GRPO, backbone=Qwen3-4B-Instruct-25072026.0243.1