Free-form Question Answering on CiQi-Bench
71.3Accuracy (Dynasty)CiQi-Agent
Evaluation results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| CiQi-AgentParameters=7B2026.03 | 71.3 | 49.1 | 69.8 | 85.4 | 49.7 | 75 | 66.7 | |
| Gemini 2.5 Pro2026.03 | 48.1 | 34.9 | 48.4 | 50.2 | 16.1 | 39 | 39.5 | |
| o32026.03 | 42.7 | 36.6 | 44.4 | 74.2 | 33.1 | 62.1 | 48.8 | |
| InternVL3.5-241B-A28B-FlashArchitecture=241B-A28B-Flash2026.03 | 42.4 | 31.6 | 36.9 | 52.6 | 19.6 | 41.5 | 37.4 | |
| GPT-52026.03 | 39.4 | 32.8 | 42.6 | 74.4 | 35.3 | 63.9 | 48 | |
| Claude Opus 42026.03 | 36.8 | 10.3 | 22 | 64.1 | 25.1 | 59.1 | 36.2 | |
| GPT-4.12026.03 | 36.7 | 27.2 | 29 | 67.5 | 27.6 | 60.1 | 41.3 | |
| GLM-4.5VParameters=106B2026.03 | 31 | 14.3 | 32.8 | 65.4 | 31.1 | 65.2 | 39.9 | |
| Qwen2.5-VL-72B-InstructParameters=72B2026.03 | 29.5 | 31.2 | 27.7 | 75.8 | 31 | 62.6 | 43 | |
| GPT-4o2026.03 | 26.9 | 13.4 | 15.1 | 53.9 | 21.1 | 47.6 | 29.7 | |
| Kimi-VL-A3B-InstructParameters=16B2026.03 | 17.3 | 23.7 | 16.2 | 69.5 | 26.5 | 61.3 | 35.7 |