List your company

Question Answering on LongMemEval 500 questions

61.4QA AccuracyDiagnostic-conditional
32.90440.30247.755.098May 5, 2026

Evaluation results

MethodLinks
Diagnostic-conditionalScale=8B2026.0561.4
Diagnostic-conditionalScale=14B2026.0560
Best unconditionalScale=8B2026.0559.8
Best unconditionalScale=14B2026.0559.8
IntactScale=14B2026.0558.6
Best unconditionalScale=4B2026.0558.2
Diagnostic-conditionalScale=4B2026.0557.4
IntactScale=8B2026.0557.4
IntactScale=4B2026.0556.2
Best unconditionalScale=0.6B2026.0534.4
Diagnostic-conditionalScale=0.6B2026.0534.4
IntactScale=0.6B2026.0534