Scientific QA on SPIQA
79.9SPIQA-AGPT-5.2
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| GPT-5.2Model=GPT-5.22026.03 | 79.9 | 75.4 | 74 | |
| GPT-5.1Model=GPT-5.12026.03 | 79.4 | 79.8 | 71.6 | |
| Qwen-3-VL-8BModel=Qwen-3-VL-8B2026.03 | 73.2 | 64 | 62.3 | |
| Qwen2.5-VL-7B + SCIMDRModel=Qwen2.5-VL-7B, Training Data=SCIMDR2026.03 | 68.6 | 58.8 | 47.3 | |
| Qwen2.5-VL-7BModel=Qwen2.5-VL-7B, Training Data=None2026.03 | 66.4 | 56.6 | 48.9 | |
| LLaVA-OV-1.5-8BModel=LLaVA-OV-1.5-8B2026.03 | 66 | 62.7 | 51.1 | |
| Qwen2.5-VL-7B + SPIQAModel=Qwen2.5-VL-7B, Training Data=SPIQA2026.03 | 62.7 | 44.7 | 40 | |
| InternVL-3-8BModel=InternVL-3-8B2026.03 | 59.6 | 46.9 | 40.8 |