Question Answering on TruthfulQA (Accuracy, Conciseness, Factual Consistency)
67.25AccuracyGemini-2.0-flash
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| Gemini-2.0-flash2026.07 | 67.25 | 58.97 | 39.75 | 61.04 | |
| DeepSeek-v32026.07 | 67.19 | 56.87 | 42.28 | 60.88 | |
| Doubao-1.5-pro-32k2026.07 | 66.89 | 54.03 | 44.45 | 58.73 | |
| QWQ Plus Latest2026.07 | 64.96 | 51.45 | 41.26 | 58 | |
| moonshot-v1-8k2026.07 | 59.05 | 49.27 | 29.36 | 54.99 |