List your company
ResearchFormerly WizWand

Question Answering on CORTEXBENCH Comparison

95.7AccuracyClaude Opus 4.6
18.63638.64358.6578.657Jun 29, 2026
Updated 4mo ago

Evaluation results

MethodLinks
Claude Opus 4.6Evaluation Setting=ORACLE2026.0695.7
GPT-5.4Evaluation Setting=ORACLE2026.0694.5
DeepSeek-V3.2Evaluation Setting=ORACLE2026.0694.1
DeepSeek-V4-FlashEvaluation Setting=ORACLE2026.0692.8
Claude Sonnet 4.6Evaluation Setting=ORACLE2026.0683.1
GPT-4oEvaluation Setting=ORACLE2026.0673.4
Gemini 3 ProEvaluation Setting=ORACLE2026.0672.2
Gemini 3.1 ProEvaluation Setting=ORACLE2026.0665.6
Claude Opus 4.6Evaluation Setting=M-SRCH2026.0657.1
Gemini 3.1 ProEvaluation Setting=1-SRCH2026.0654.1
GPT-5.4Evaluation Setting=M-SRCH2026.0651.6
Gemini 3 ProEvaluation Setting=M-SRCH2026.0650.9
DeepSeek-V4-FlashEvaluation Setting=M-SRCH2026.0649.1
GPT-5.4Evaluation Setting=1-SRCH2026.0648.4
DeepSeek-V3.2Evaluation Setting=M-SRCH2026.0647.2
Claude Sonnet 4.6Evaluation Setting=1-SRCH2026.0641.9
Claude Sonnet 4.6Evaluation Setting=M-SRCH2026.0641
Claude Opus 4.6Evaluation Setting=1-SRCH2026.0641
Gemini 3.1 ProEvaluation Setting=M-SRCH2026.0640.4
GPT-5.4Evaluation Setting=CLOSED2026.0632.3
Claude Opus 4.6Evaluation Setting=CLOSED2026.0631.7
Gemini 3 ProEvaluation Setting=1-SRCH2026.0631.3
DeepSeek-V4-FlashEvaluation Setting=1-SRCH2026.0630.3
DeepSeek-V3.2Evaluation Setting=1-SRCH2026.0628.8
Gemini 3 ProEvaluation Setting=CLOSED2026.0628.6
GPT-4oEvaluation Setting=M-SRCH2026.0628.1
Claude Sonnet 4.6Evaluation Setting=CLOSED2026.0625
DeepSeek-V4-FlashEvaluation Setting=CLOSED2026.0624.8
Gemini 3.1 ProEvaluation Setting=CLOSED2026.0624.3
GPT-4oEvaluation Setting=1-SRCH2026.0623.1
DeepSeek-V3.2Evaluation Setting=CLOSED2026.0622.6
GPT-4oEvaluation Setting=CLOSED2026.0621.6