List your company

Programming on LiveCodeBench V3 V4 (test)

61.4AccuracyT3-Struct
36.64843.07449.555.926May 5, 2026

Evaluation results

MethodLinks
T3-StructModel=GPT-OSS 120B2026.0561.46
CompactDSModel=GPT-52026.0560.96.1
Chunked traj.Model=GPT-52026.0560.96.1
T3-SemanticModel=GPT-OSS 120B2026.0560.95.2
T3-StructModel=GPT-52026.0560.45.2
Wikipedia-DPRModel=GPT-52026.0559.94.4
Tavily Search APIModel=GPT-OSS 120B2026.0559.93.5
T3-ReflectModel=GPT-52026.0559.94.4
Wikipedia-DPRModel=GPT-OSS 120B2026.0559.42.6
OpenWebMathModel=GPT-52026.0558.92.6
Wikipedia-RPJModel=GPT-52026.0558.92.6
Wikipedia-RPJModel=GPT-OSS 120B2026.0558.91.7
Full traj.Model=GPT-OSS 120B2026.0558.91.7
Chunked traj.Model=GPT-OSS 120B2026.0558.91.7
T3-SemanticModel=GPT-52026.0558.92.6
Tavily Search APIModel=GPT-52026.0558.41.7
T3-ReflectModel=GPT-OSS 120B2026.0558.40.9
No RAGModel=GPT-OSS 120B2026.0557.9—
ArxivModel=GPT-52026.0557.90.9
Full traj.Model=GPT-52026.0557.90.9
No RAGModel=GPT-52026.0557.4—
StackExchangeModel=GPT-52026.0557.40
ArxivModel=GPT-OSS 120B2026.0557.4-0.9
CompactDSModel=GPT-OSS 120B2026.0557.4-0.9
GitHubModel=GPT-52026.0556.9-0.9
StackExchangeModel=GPT-OSS 120B2026.0555-5
GitHubModel=GPT-OSS 120B2026.0554.5-5.9
Chunked traj.Model=Gemini-2.5 Flash2026.05486.4
Tavily Search APIModel=Gemini-2.5 Flash2026.0547.96.2
T3-StructModel=Gemini-2.5 Flash2026.05474.2
ArxivModel=Gemini-2.5 Flash2026.0546.94
Wikipedia-DPRModel=Gemini-2.5 Flash2026.0546.53.1
Full traj.Model=Gemini-2.5 Flash2026.0546.53.1
CompactDSModel=Gemini-2.5 Flash2026.0545.40.7
No RAGModel=Gemini-2.5 Flash2026.0545.1—
Wikipedia-RPJModel=Gemini-2.5 Flash2026.0545-0.2
T3-ReflectModel=Gemini-2.5 Flash2026.0545-0.2
T3-SemanticModel=Gemini-2.5 Flash2026.0545-0.2
StackExchangeModel=Gemini-2.5 Flash2026.0542.1-6.7
GitHubModel=Gemini-2.5 Flash2026.0542.1-6.7
OpenWebMathModel=Gemini-2.5 Flash2026.0539.6-12.2
OpenWebMathModel=GPT-OSS 120B2026.0537.6-35.1