List your company

Truthfulness Evaluation on TruthfulQA (Metric: TruthfulQA)

82.6TruthfulQA ScoreCouncil Mode
48.48857.34466.275.056Feb 17, 2026Feb 24, 2026Mar 4, 2026Mar 11, 2026Mar 19, 2026Mar 26, 2026Apr 3, 2026

Evaluation results

MethodLinks
Council ModeLatency (s)=8.42026.0482.6
Claude Opus 4.6Latency (s)=4.12026.0474.8
GPT-5.4Latency (s)=3.22026.0471.2
Gemini 3.1 ProLatency (s)=2.82026.0468.5
DeepSeek V3.2Latency (s)=5.62026.0465.3
Seed 2.0 ProLatency (s)=3.82026.0463.1
Adam-NSCLData=ZsRE 10K2026.0254
AlphaEditData=ZsRE 10K2026.0253.9
LLaMA-3-8B-InstructData=ZsRE 10K2026.0250.7
LocBF-FTData=ZsRE 10K2026.0250.7
CrispEditData=ZsRE 10K2026.0250.2
UltraEditData=ZsRE 10K2026.0249.8