Multimodal Question Answering on CRIT Scientific Paper 1.0 (test)
15.9EMQwen2.5-VL_CRIT
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Qwen2.5-VL_CRITModel Parameters=7B, Evaluation Setting=CoT, Fine-tuned on CRIT=Yes2026.04 | 15.9 | 22.5 | |
| Idefics2_CRITModel Parameters=8B, Evaluation Setting=CoT, Fine-tuned on CRIT=Yes2026.04 | 12.3 | 20.2 | |
| Gemini 2.0 FlashEvaluation Setting=CoT2026.04 | 11.5 | 13.7 | |
| GPT-4o-miniEvaluation Setting=CoT2026.04 | 9.7 | 13.1 | |
| Qwen2.5-VLModel Parameters=72B, Evaluation Setting=CoT2026.04 | 9.4 | 12.3 | |
| GPT-4oEvaluation Setting=CoT2026.04 | 8.4 | 14 | |
| LLaVA-OnevisionModel Parameters=7B, Evaluation Setting=CoT2026.04 | 7.1 | 10.1 | |
| Qwen2.5-VLModel Parameters=7B, Evaluation Setting=CoT2026.04 | 6.8 | 9.6 | |
| Intern2.5-VLModel Parameters=8B, Evaluation Setting=CoT2026.04 | 5.5 | 9.8 | |
| Idefics2Model Parameters=8B, Evaluation Setting=CoT2026.04 | 3.4 | 6.1 | |
| Phi3.5-VisionModel Parameters=4B, Evaluation Setting=CoT2026.04 | 3.1 | 5.9 |