List your company

Mathematical Reasoning on FinanceMath

64AccuracyF-1
24.4834.744555.26Jan 27, 2026

Evaluation results

MethodLinks
F-1Model=GPT-5, Model Category=Proprietary2026.0164
F-1Model=Qwen3-235B, Model Category=Open Source2026.0161
PoTModel=Qwen3-235B, Model Category=Open Source2026.0159.5
F-1Model=Gemini 2.5 Pro, Model Category=Proprietary2026.0156.5
CoTModel=Gemini 2.5 Pro, Model Category=Proprietary2026.0156
F-1Model=Qwen3-30B, Model Category=Open Source2026.0156
PoTModel=Gemini 2.5 Pro, Model Category=Proprietary2026.0155.5
PoTModel=GPT-5, Model Category=Proprietary2026.0154
CoTModel=Qwen3-30B, Model Category=Open Source2026.0153.5
PoTModel=Qwen3-30B, Model Category=Open Source2026.0153.5
F-1Model=DeepSeek-V3.1, Model Category=Open Source2026.0144
CoTModel=GPT-5, Model Category=Proprietary2026.0142.5
PoTModel=DeepSeek-V3.1, Model Category=Open Source2026.0137.5
Zero-ShotModel=Qwen3-235B, Model Category=Open Source2026.0135.5
CoTModel=Qwen3-235B, Model Category=Open Source2026.0135
Zero-ShotModel=Gemini 2.5 Pro, Model Category=Proprietary2026.0132.5
Zero-ShotModel=Qwen3-30B, Model Category=Open Source2026.0128.5
CoTModel=DeepSeek-V3.1, Model Category=Open Source2026.0128
Zero-ShotModel=DeepSeek-V3.1, Model Category=Open Source2026.0127.5
Zero-ShotModel=GPT-5, Model Category=Proprietary2026.0126