List your company

Information Retrieval on FRAMES

81.5RecallGPT-5.4
13.79631.37348.9566.527Jun 1, 2026

Evaluation results

MethodLinks
GPT-5.4Category=Frontier models2026.0681.581.586.5
Opus-4.6Category=Frontier models2026.0681.481.487.8
Sonnet-4.6Category=Frontier models2026.0678.778.785.9
Harness-1Parameters=20B, Category=Open-source small models2026.06717174.9
Kimi-K2.5Category=Frontier models2026.0669.769.784
Context-1Parameters=20B, Category=Open-source small models2026.0663.863.878.7
Tongyi DeepResearchParameters=30B, Category=Open-source small models2026.0656.156.165.4
GPT-OSSParameters=120B, Category=Frontier models2026.0649.549.586.3
GPT-OSSParameters=20B, Category=Open-source small models2026.0639.139.170.2
Search-R1Parameters=32B, Category=Open-source small models2026.0632.932.932.9
Qwen3Parameters=32B, Category=Open-source small models2026.0616.416.440.2