Visual Mathematical Reasoning on FlowVerse DI+RP+EI+OQ (All)
34.4CoT Error
Qwen-VL-Plus
Updated 1mo ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2025.03 | 34.4 | 27.1 | |
2025.03 | 36.5 | 28.8 | |
2025.03 | 38 | 29.9 | |
2025.03 | 39 | 23.5 | |
2025.03 | 43 | 36.3 | |
2025.03 | 44 | 34.2 | |
2025.03 | 44.7 | 41 | |
2025.03 | 46 | 39.4 | |
2025.03 | 50.7 | 41.2 | |
2025.03 | 51.3 | 44.5 | |
2025.03 | 52.3 | 48.6 | |
2025.03 | 53.8 | 42.2 | |
2025.03 | 54.7 | 50.1 | |
2025.03 | 55.1 | 47.8 | |
2025.03 | 56.2 | 53.4 | |
2025.03 | 56.9 | 49.6 | |
2025.03 | 57 | 46 | |
2025.03 | 62 | 55.3 | |
2025.03 | 65.8 | 60.1 | |
2025.03 | 66.5 | 61.8 |