List your company

Mathematical Reasoning on AIME 2025-2026 (test)

93.3AccuracyT3-Reflect
39.63653.56867.581.432May 5, 2026

Evaluation results

MethodLinks
T3-ReflectModel=GPT-52026.0593.37.6
GitHubModel=GPT-52026.0591.75.8
Chunked traj.Model=GPT-52026.0591.75.8
T3-StructModel=GPT-52026.0591.75.8
Wikipedia-RPJModel=GPT-52026.05903.8
Wikipedia-DPRModel=GPT-52026.0588.31.8
CompactDSModel=GPT-52026.0588.31.8
T3-SemanticModel=GPT-52026.0588.31.8
No RAGModel=GPT-52026.0586.7—
Full traj.Model=GPT-52026.0586.70
OpenWebMathModel=GPT-52026.0585-2
ArxivModel=GPT-52026.0585-2
Chunked traj.Model=GPT-OSS 120B2026.05858.6
StackExchangeModel=GPT-52026.0583.3-3.9
Tavily Search APIModel=GPT-52026.0583.3-3.9
T3-SemanticModel=GPT-OSS 120B2026.0583.36.4
T3-SemanticModel=Gemini-2.5 Flash2026.0583.356.3
T3-StructModel=GPT-OSS 120B2026.0581.74.3
T3-ReflectModel=GPT-OSS 120B2026.0581.74.3
CompactDSModel=GPT-OSS 120B2026.05802.2
Chunked traj.Model=Gemini-2.5 Flash2026.058050.1
No RAGModel=GPT-OSS 120B2026.0578.3—
ArxivModel=GPT-OSS 120B2026.0578.30
StackExchangeModel=GPT-OSS 120B2026.0576.7-2
Wikipedia-RPJModel=GPT-OSS 120B2026.0576.7-2
GitHubModel=GPT-OSS 120B2026.0576.7-2
T3-ReflectModel=Gemini-2.5 Flash2026.0576.743.9
Tavily Search APIModel=GPT-OSS 120B2026.0575-4.2
Full traj.Model=GPT-OSS 120B2026.0573.3-6.4
Full traj.Model=Gemini-2.5 Flash2026.0573.337.5
T3-StructModel=Gemini-2.5 Flash2026.0573.337.5
Wikipedia-DPRModel=GPT-OSS 120B2026.0571.7-8.4
OpenWebMathModel=GPT-OSS 120B2026.0563.3-19.2
GitHubModel=Gemini-2.5 Flash2026.056012.6
Tavily Search APIModel=Gemini-2.5 Flash2026.056012.6
CompactDSModel=Gemini-2.5 Flash2026.0558.39.4
Wikipedia-DPRModel=Gemini-2.5 Flash2026.0556.76.4
No RAGModel=Gemini-2.5 Flash2026.0553.3—
ArxivModel=Gemini-2.5 Flash2026.0551.7-3
StackExchangeModel=Gemini-2.5 Flash2026.0546.7-12.4
OpenWebMathModel=Gemini-2.5 Flash2026.0545-15.6
Wikipedia-RPJModel=Gemini-2.5 Flash2026.0541.7-21.8