List your company
ResearchFormerly WizWand

Multimodal Reasoning on Geo3k

62.23Pass@1MiMo-VL-8B
24.852434.556244.2653.9638May 12, 2026
Updated 6mo ago

Evaluation results

MethodLinks
MiMo-VL-8BModel Size=~8B, Decoding Strategy=greedy, Max Length=40962026.0562.23
Self-distill Masking-KD-8BModel Size=~8B, Decoding Strategy=greedy, Max Length=4096, Distillation=Self-distill2026.0558.24
Qwen3-VL-8B-ThinkingModel Size=~8B, Decoding Strategy=greedy, Max Length=40962026.0554.58
Masking-KD-4BModel Size=~4B, Decoding Strategy=greedy, Max Length=4096, Distillation=Distilled from 8B2026.0552.58
InternVL3.5-8BModel Size=~8B, Decoding Strategy=greedy, Max Length=40962026.0544.59
Qwen3-VL-4B-ThinkingModel Size=~4B, Decoding Strategy=greedy, Max Length=40962026.0543.93
Ovis2-8BModel Size=~8B, Decoding Strategy=greedy, Max Length=40962026.0542.43
InternVL3.5-4BModel Size=~4B, Decoding Strategy=greedy, Max Length=40962026.0541.93
Masking-KD-2BModel Size=~2B, Decoding Strategy=greedy, Max Length=4096, Distillation=Distilled from 8B2026.0540.93
Qwen2.5-VL-7BModel Size=~8B, Decoding Strategy=greedy, Max Length=40962026.0540.43
InternVL3-8BModel Size=~8B, Decoding Strategy=greedy, Max Length=40962026.0538.44
Ovis2-4BModel Size=~4B, Decoding Strategy=greedy, Max Length=40962026.0537.77
InternVL3-2BModel Size=~2B, Decoding Strategy=greedy, Max Length=40962026.0533.78
Ovis2-2BModel Size=~2B, Decoding Strategy=greedy, Max Length=40962026.0531.11
InternVL3.5-2BModel Size=~2B, Decoding Strategy=greedy, Max Length=40962026.0529.95
Qwen2.5-VL-3BModel Size=~4B, Decoding Strategy=greedy, Max Length=40962026.0526.29
Qwen3-VL-2B-ThinkingModel Size=~2B, Decoding Strategy=greedy, Max Length=40962026.0526.29