List your company

Question Answering on CORTEXBENCH Bridge

96.1AccuracyGPT-5.4
23.8242.58561.3580.115Jun 29, 2026

Evaluation results

MethodLinks
GPT-5.4Evaluation Setting=ORACLE2026.0696.1
DeepSeek-V3.2Evaluation Setting=ORACLE2026.0694.8
Claude Opus 4.6Evaluation Setting=ORACLE2026.0691.9
DeepSeek-V4-FlashEvaluation Setting=ORACLE2026.0690.2
Claude Sonnet 4.6Evaluation Setting=ORACLE2026.0684
Gemini 3.1 ProEvaluation Setting=ORACLE2026.0682.5
Gemini 3 ProEvaluation Setting=ORACLE2026.0680.1
GPT-4oEvaluation Setting=ORACLE2026.0677.5
Gemini 3.1 ProEvaluation Setting=1-SRCH2026.0665.7
Gemini 3 ProEvaluation Setting=M-SRCH2026.0663
Claude Opus 4.6Evaluation Setting=M-SRCH2026.0662.5
GPT-5.4Evaluation Setting=M-SRCH2026.0660.9
Claude Sonnet 4.6Evaluation Setting=M-SRCH2026.0659.1
GPT-5.4Evaluation Setting=1-SRCH2026.0658.4
DeepSeek-V4-FlashEvaluation Setting=M-SRCH2026.0654.1
Gemini 3.1 ProEvaluation Setting=M-SRCH2026.0652.5
Claude Sonnet 4.6Evaluation Setting=1-SRCH2026.0652.5
DeepSeek-V3.2Evaluation Setting=M-SRCH2026.0652.2
Claude Opus 4.6Evaluation Setting=1-SRCH2026.0650.9
GPT-5.4Evaluation Setting=CLOSED2026.0647.2
DeepSeek-V4-FlashEvaluation Setting=1-SRCH2026.0644
DeepSeek-V3.2Evaluation Setting=1-SRCH2026.0641.3
Gemini 3 ProEvaluation Setting=1-SRCH2026.0638.1
Claude Opus 4.6Evaluation Setting=CLOSED2026.0635.3
Claude Sonnet 4.6Evaluation Setting=CLOSED2026.0634.7
GPT-4oEvaluation Setting=M-SRCH2026.0633.8
DeepSeek-V4-FlashEvaluation Setting=CLOSED2026.0630.9
Gemini 3 ProEvaluation Setting=CLOSED2026.0630.9
DeepSeek-V3.2Evaluation Setting=CLOSED2026.0630.3
Gemini 3.1 ProEvaluation Setting=CLOSED2026.0628.1
GPT-4oEvaluation Setting=1-SRCH2026.0626.9
GPT-4oEvaluation Setting=CLOSED2026.0626.6