Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Visual Mathematical Reasoning on MathVision (BoN@8)
Loading...
43.6
BoN@8 Accuracy
Gemini-2.0-Flash
15.936
23.118
30.3
37.482
Mar 17, 2026
BoN@8 Accuracy
Delta (BoN@8 - Pass@1)
Updated 1mo ago
Evaluation Results
Method
Method
Links
BoN@8 Accuracy
Delta (BoN@8 - Pass@1)
Gemini-2.0-Flash
Reranking Strategy=Bes...
2026.03
43.6
-
InternVL2.5-38B + EVPV-PRM
Policy Model=InternVL2...
2026.03
37.59
5.39
Claude-3.5-Sonnet
Reranking Strategy=Bes...
2026.03
35.6
-
InternVL2.5-38B + VisualPRM
Policy Model=InternVL2...
2026.03
35.2
3
InternVL2.5-38B
Policy Model=InternVL2...
2026.03
32.2
-
GPT-4o
Reranking Strategy=Bes...
2026.03
31.2
-
InternVL2.5-26B + VisualPRM
Policy Model=InternVL2...
2026.03
29.6
6.2
InternVL2.5-26B + EVPV-PRM
Policy Model=InternVL2...
2026.03
28.11
4.71
InternVL2.5-8B + VisualPRM
Policy Model=InternVL2...
2026.03
25.7
8.7
InternVL2.5-26B
Policy Model=InternVL2...
2026.03
23.4
-
InternVL2.5-8B + EVPV-PRM
Policy Model=InternVL2...
2026.03
22.07
5.07
InternVL2.5-8B
Policy Model=InternVL2...
2026.03
17
-
Feedback
Search any
task
Search any
task