List your company

Question Answering on TruthfulQA (ACC, JCD, F&C, C&A, ARS)

93.67ACCMixture-of-Agents
79.1182.8986.6790.45May 8, 2026

Evaluation results

MethodLinks
Mixture-of-Agents2026.0593.6786.4290.3286.6489.97
GEMINI-3.1-PRO2026.0592.3389.4391.3788.1193.13
DEEPSEEK-R12026.059084.6288.1984.0489.28
GPT-5.12026.059087.5390.7687.5492.3
MAVEN2026.059090.7790.989.3796.38
Self-Discover2026.0587.3386.9188.8485.0290.05
Multi-LLM Collab2026.058787.3289.0786.1891.57
Self-Detection2026.058787.0488.6285.7890.43
DEEPSEEK-V3.22026.0585.6782.8287.5283.4885.97
LMVSLM2026.0584.3387.5788.1884.9990.63
ReConcile2026.0579.6779.8183.3775.4684.35