Document Understanding on CharXiv reas.
0.686AccuracyGPT5 mini
Evaluation Results
| Method | Links | |
|---|---|---|
| GPT5 miniModel Source Category=Closed-source VLMs, Evaluation Mode=Thinking Mode2026.01 | 0.686 | |
| Qwen3-VL 32BModel Source Category=Open-weight VLMs, Model Parameters=32B, Evaluation Mode=Thinking Mode2026.01 | 0.652 | |
| Gemini-2.5 FlashModel Source Category=Closed-source VLMs, Evaluation Mode=Thinking Mode2026.01 | 0.617 | |
| MMFineReason-8BModel Source Category=Ours, Model Parameters=8B, Evaluation Mode=Thinking Mode2026.01 | 0.6 | |
| MMFineReason-4BModel Source Category=Ours, Model Parameters=4B, Evaluation Mode=Thinking Mode2026.01 | 0.581 | |
| Qwen3-VL 30B-A3BModel Source Category=Open-weight VLMs, Model Parameters=30B-A3B, Evaluation Mode=Thinking Mode2026.01 | 0.566 | |
| Qwen3-VL 8BModel Source Category=Open-weight VLMs, Model Parameters=8B, Evaluation Mode=Thinking Mode2026.01 | 0.53 | |
| MMR1 8BModel Source Category=Open-source VLMs, Model Parameters=8B, Evaluation Mode=Thinking Mode2026.01 | 0.488 | |
| HoneyBee 8BModel Source Category=Open-source VLMs, Model Parameters=8B, Evaluation Mode=Thinking Mode2026.01 | 0.474 | |
| OMR 7BModel Source Category=Open-source VLMs, Model Parameters=7B, Evaluation Mode=Thinking Mode2026.01 | 0.461 | |
| MMFineReason-2BModel Source Category=Ours, Model Parameters=2B, Evaluation Mode=Thinking Mode2026.01 | 0.454 |