Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multimodal long-horizon complex reasoning on MM-BrowseComp
Loading...
41.1
Score
Claude-4.6-Sonnet-Thinking
5.324
14.612
23.9
33.188
Jun 13, 2026
Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Score
Claude-4.6-Sonnet-Thinking
Size=-, Train=-
2026.06
41.1
DeepSeek-V3.2
Size=671B, Train=-
2026.06
31.7
Doubao-2.0-Pro
Size=-, Train=-
2026.06
27.2
Qwen3.5-397B
Size=397B, Train=-
2026.06
27.2
REDSearcher-MM-SFT
Size=30B, Train=Mid/SFT
2026.06
25.3
GLM-5
Size=744B, Train=-
2026.06
22.8
GPT-5.2
Size=-, Train=-
2026.06
22.3
Kimi-K2.5
Size=1T, Train=-
2026.06
20.5
MiniMax-M2.7
Size=230B, Train=-
2026.06
20.1
S1-DeepResearch
Size=32B, Train=SFT
2026.06
19.2
Gemini-3.1-Pro-Preview
Size=-, Train=-
2026.06
11.6
Qwen3-32B
Size=32B, Train=-
2026.06
7.1
Qwen3-235B
Size=235B, Train=-
2026.06
6.7
Feedback
Search any
task
Search any
task