List your company

Question Answering on TruthfulQA (Accuracy, Conciseness, Factual Consistency)

67.25AccuracyGemini-2.0-flash
58.72260.93663.1565.364Jul 8, 2026

Evaluation results

MethodLinks
Gemini-2.0-flash2026.0767.2558.9739.7561.04
DeepSeek-v32026.0767.1956.8742.2860.88
Doubao-1.5-pro-32k2026.0766.8954.0344.4558.73
QWQ Plus Latest2026.0764.9651.4541.2658
moonshot-v1-8k2026.0759.0549.2729.3654.99