Mathematical Reasoning on MathVista (Score, #F)
72.2ScoreBaseline
Evaluation results
| Method | Links | ||
|---|---|---|---|
| BaselineCheckpoint=VL-Rethinker [18], Pruning rate (ρ)=0%, Rollouts (K)=12026.06 | 72.2 | 100 | |
| AVISCheckpoint=VL-Rethinker [18], Pruning rate (ρ)=Adaptive, Rollouts (K)=Adaptive2026.06 | 71.8 | 43 | |
| AVISCheckpoint=OpenVLThinker [75], Pruning rate (ρ)=Adaptive, Rollouts (K)=Adaptive2026.06 | 70.6 | 41 | |
| FixedCheckpoint=VL-Rethinker [18], Pruning rate (ρ)=75%, Rollouts (K)=52026.06 | 69.9 | 88 | |
| FixedCheckpoint=OpenVLThinker [75], Pruning rate (ρ)=75%, Rollouts (K)=52026.06 | 69.8 | 79 | |
| AVISCheckpoint=Vision-R1 [5], Pruning rate (ρ)=Adaptive, Rollouts (K)=Adaptive2026.06 | 69.6 | 39 | |
| FixedCheckpoint=Vision-R1 [5], Pruning rate (ρ)=75%, Rollouts (K)=52026.06 | 69.3 | 81 | |
| FixedCheckpoint=Qwen 2.5 VL [1], Pruning rate (ρ)=75%, Rollouts (K)=52026.06 | 68.9 | 83 | |
| BaselineCheckpoint=OpenVLThinker [75], Pruning rate (ρ)=0%, Rollouts (K)=12026.06 | 68.7 | 100 | |
| BaselineCheckpoint=Vision-R1 [5], Pruning rate (ρ)=0%, Rollouts (K)=12026.06 | 68.5 | 100 | |
| AVISCheckpoint=Qwen 2.5 VL [1], Pruning rate (ρ)=Adaptive, Rollouts (K)=Adaptive2026.06 | 68.1 | 46 | |
| BaselineCheckpoint=Qwen 2.5 VL [1], Pruning rate (ρ)=0%, Rollouts (K)=12026.06 | 67.5 | 100 |