List your company
ResearchFormerly WizWand

Multimodal Reasoning on MathVerse (Pass@1)

67.84Pass@1Self-distill Masking-KD-8B
16.131229.555642.9856.4044May 12, 2026
Updated 6mo ago

Evaluation results

MethodLinks
Self-distill Masking-KD-8BModel Size=~8B, Decoding Strategy=greedy, Max Length=4096, Distillation=Self-distill2026.0567.84
Qwen3-VL-8B-ThinkingModel Size=~8B, Decoding Strategy=greedy, Max Length=40962026.0563.81
Masking-KD-4BModel Size=~4B, Decoding Strategy=greedy, Max Length=4096, Distillation=Distilled from 8B2026.0562.66
Ovis2-8BModel Size=~8B, Decoding Strategy=greedy, Max Length=40962026.0561.19
Ovis2-4BModel Size=~4B, Decoding Strategy=greedy, Max Length=40962026.0558.03
Masking-KD-2BModel Size=~2B, Decoding Strategy=greedy, Max Length=4096, Distillation=Distilled from 8B2026.0557.89
InternVL3-8BModel Size=~8B, Decoding Strategy=greedy, Max Length=40962026.0554.82
InternVL3.5-8BModel Size=~8B, Decoding Strategy=greedy, Max Length=40962026.0553.26
Ovis2-2BModel Size=~2B, Decoding Strategy=greedy, Max Length=40962026.0550.32
Qwen3-VL-4B-ThinkingModel Size=~4B, Decoding Strategy=greedy, Max Length=40962026.0549.86
InternVL3.5-4BModel Size=~4B, Decoding Strategy=greedy, Max Length=40962026.0543.21
Qwen2.5-VL-3BModel Size=~4B, Decoding Strategy=greedy, Max Length=40962026.0540.69
InternVL3-2BModel Size=~2B, Decoding Strategy=greedy, Max Length=40962026.0540.37
Qwen2.5-VL-7BModel Size=~8B, Decoding Strategy=greedy, Max Length=40962026.0538.67
Qwen3-VL-2B-ThinkingModel Size=~2B, Decoding Strategy=greedy, Max Length=40962026.0528.21
InternVL3.5-2BModel Size=~2B, Decoding Strategy=greedy, Max Length=40962026.0527.94
MiMo-VL-8BModel Size=~8B, Decoding Strategy=greedy, Max Length=40962026.0518.12