Multimodal Mathematical Reasoning on MathVision mini (test)
29.6AccuracyVideoAuto-R1
Evaluation Results
| Method | Links | |
|---|---|---|
| VideoAuto-R1Backbone=Qwen2.5-VL-7B2026.01 | 29.6 | |
| Qwen2.5-VL-7BBackbone=Qwen2.5-VL-7B2026.01 | 26.3 |
Loading the SOTA2 catalog…
| Method | Links | |
|---|---|---|
| VideoAuto-R1Backbone=Qwen2.5-VL-7B2026.01 | 29.6 | |
| Qwen2.5-VL-7BBackbone=Qwen2.5-VL-7B2026.01 | 26.3 |