Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multimodal long-horizon complex reasoning on LiveVQA
Loading...
81.3
Score
Claude-4.6-Sonnet-Thinking
49.06
57.43
65.8
74.17
Jun 13, 2026
Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Score
Claude-4.6-Sonnet-Thinking
Size=-, Train=-
2026.06
81.3
REDSearcher-MM-SFT
Size=30B, Train=Mid/SFT
2026.06
78.5
Vision-DeepResearch
Size=30B, Train=SFT/RL
2026.06
77.6
GLM-5
Size=744B, Train=-
2026.06
77
Qwen3.5-397B
Size=397B, Train=-
2026.06
75.7
MiniMax-M2.7
Size=230B, Train=-
2026.06
69.7
MM-DeepResearch
Size=32B, Train=SFT/RL
2026.06
68
S1-DeepResearch
Size=32B, Train=SFT
2026.06
67.7
Gemini-3.1-Pro-Preview
Size=-, Train=-
2026.06
66.7
GPT-5.2
Size=-, Train=-
2026.06
56.7
Kimi-K2.5
Size=1T, Train=-
2026.06
56.3
Qwen3-235B
Size=235B, Train=-
2026.06
52
Doubao-2.0-Pro
Size=-, Train=-
2026.06
50.9
DeepSeek-V3.2
Size=671B, Train=-
2026.06
50.7
Qwen3-32B
Size=32B, Train=-
2026.06
50.3
Feedback
Search any
task
Search any
task