List your company

Trace-quality Evaluation on Trace-quality Dataset (evaluation set)

7.96FactualityClaude S. 4.6
7.13847.35177.5657.7783Jun 10, 2026

Evaluation results

MethodLinks
Claude S. 4.62026.067.967.917.897.937.987.957.94391
GPT-4o2026.067.87.397.787.077.757.637.57392
Gemini 2.52026.067.697.217.157.087.577.647.39399
MARD-7B2026.067.176.057.297.036.86.496.8586