Scientific QA on CharXiv
95.2CharXiv-D ScoreGPT-5.2
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| GPT-5.2Model=GPT-5.22026.03 | 95.2 | 73.1 | |
| GPT-5.1Model=GPT-5.12026.03 | 90.9 | 58.3 | |
| Qwen2.5-VL-7B + SCIMDRModel=Qwen2.5-VL-7B, Training Data=SCIMDR2026.03 | 75.6 | 37.9 | |
| Qwen-3-VL-8BModel=Qwen-3-VL-8B2026.03 | 74.2 | 40.1 | |
| InternVL-3-8BModel=InternVL-3-8B2026.03 | 66.7 | 34.6 | |
| LLaVA-OV-1.5-8BModel=LLaVA-OV-1.5-8B2026.03 | 66.3 | 32.9 | |
| Qwen2.5-VL-7BModel=Qwen2.5-VL-7B, Training Data=None2026.03 | 65 | 37.7 | |
| Qwen2.5-VL-7B + SPIQAModel=Qwen2.5-VL-7B, Training Data=SPIQA2026.03 | 50.9 | 33.3 |