List your company

Meeting claim evaluation on city_council & private_data overall (test)

75.4Accuracygpt-5.4
73.8474.24574.6575.055Apr 23, 2026

Evaluation results

MethodLinks
gpt-5.4Meetings=56, Evaluator runs=1122026.0475.484.486.8
gpt-4.1Meetings=56, Evaluator runs=1122026.0473.978.979.4