List your company

Mathematical Reasoning on AIME 2023-2025 (pass@4)

11.11pass@4 AccuracySAGC
5.3386.83658.3359.8335Jun 1, 2026

Evaluation results

MethodLinks
SAGCBackbone=Llama3.2-3b, Algorithm=DAPO, Group Size=Dynamic2026.0611.11
SAGCBackbone=Qwen2.5-3b, Algorithm=DAPO, Group Size=Dynamic2026.0610
OpenRLHFBackbone=Llama3.2-3b, Algorithm=DAPO, Group Size=162026.0610
OpenRLHFBackbone=Qwen2.5-3b, Algorithm=DAPO, Group Size=162026.068.89
OpenRLHFBackbone=Llama3.2-3b, Algorithm=GRPO, Group Size=162026.068.89
OpenRLHFBackbone=Qwen2.5-3b, Algorithm=GRPO, Group Size=162026.067.78
SAGCBackbone=Qwen2.5-3b, Algorithm=GRPO, Group Size=Dynamic2026.067.78
OpenRLHFBackbone=Llama3.2-3b, Algorithm=GRPO, Group Size=82026.067.78
SAGCBackbone=Llama3.2-3b, Algorithm=GRPO, Group Size=Dynamic2026.067.78
OpenRLHFBackbone=Qwen2.5-3b, Algorithm=GRPO, Group Size=42026.066.67
OpenRLHFBackbone=Qwen2.5-3b, Algorithm=GRPO, Group Size=82026.066.67
OpenRLHFBackbone=Llama3.2-3b, Algorithm=GRPO, Group Size=42026.066.67
OpenRLHFBackbone=Llama3.2-3b, Algorithm=DAPO, Group Size=42026.066.67
OpenRLHFBackbone=Llama3.2-3b, Algorithm=DAPO, Group Size=82026.066.67
OpenRLHFBackbone=Qwen2.5-3b, Algorithm=DAPO, Group Size=42026.065.56
OpenRLHFBackbone=Qwen2.5-3b, Algorithm=DAPO, Group Size=82026.065.56