List your company

Self-Verification on MATH

88.3Pass@1FABSVer-7B
16.22834.93953.6572.361May 27, 2026

Evaluation results

MethodLinks
FABSVer-7BBackbone=Qwen2.5-7B, Training=FABSVer2026.0588.3
FABSVer-3BBackbone=Qwen2.5-3B, Training=FABSVer2026.0585.2
RISE-7BBackbone=Qwen2.5-7B, Training=RISE2026.0583.8
GPT-4oModel=GPT-4o2026.0583.4
FABSVer-1.5BBackbone=Qwen2.5-1.5B, Training=FABSVer2026.0581
RISE-3BBackbone=Qwen2.5-3B, Training=RISE2026.0581
Qwen2.5-7B InstructBackbone=Qwen2.5-7B, Training=Instruct2026.0577.2
RISE-1.5BBackbone=Qwen2.5-1.5B, Training=RISE2026.0575.9
Qwen2.5-7B Zero-RLBackbone=Qwen2.5-7B, Training=Zero-RL2026.0575.9
Qwen2.5-3B InstructBackbone=Qwen2.5-3B, Training=Instruct2026.0565.6
Qwen2.5-3B Zero-RLBackbone=Qwen2.5-3B, Training=Zero-RL2026.0564.9
Qwen2.5-7B BaseBackbone=Qwen2.5-7B, Training=Base2026.0558.4
Qwen2.5-1.5B Zero-RLBackbone=Qwen2.5-1.5B, Training=Zero-RL2026.0554.1
Qwen2.5-1.5B InstructBackbone=Qwen2.5-1.5B, Training=Instruct2026.0548.8
Qwen2.5-7B SFTBackbone=Qwen2.5-7B, Training=SFT2026.0540.5
Qwen2.5-3B BaseBackbone=Qwen2.5-3B, Training=Base2026.0539.5
Qwen2.5-3B SFTBackbone=Qwen2.5-3B, Training=SFT2026.0521.5
Qwen2.5-1.5B BaseBackbone=Qwen2.5-1.5B, Training=Base2026.0519.4
Qwen2.5-1.5B SFTBackbone=Qwen2.5-1.5B, Training=SFT2026.0519