Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multimodal long-horizon complex reasoning on HLE-VL
Loading...
25.1
Score
Gemini-3.1-Pro-Preview
8.98
13.165
17.35
21.535
Jun 13, 2026
Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Score
Gemini-3.1-Pro-Preview
Size=-, Train=-
2026.06
25.1
Claude-4.6-Sonnet-Thinking
Size=-, Train=-
2026.06
24.3
REDSearcher-MM-SFT
Size=30B, Train=Mid/SFT
2026.06
24.2
Kimi-K2.5
Size=1T, Train=-
2026.06
22.3
GPT-5.2
Size=-, Train=-
2026.06
20.8
GLM-5
Size=744B, Train=-
2026.06
19.9
Qwen3.5-397B
Size=397B, Train=-
2026.06
18.7
Doubao-2.0-Pro
Size=-, Train=-
2026.06
17.5
S1-DeepResearch
Size=32B, Train=SFT
2026.06
15.2
DeepSeek-V3.2
Size=671B, Train=-
2026.06
14.9
MiniMax-M2.7
Size=230B, Train=-
2026.06
13.1
Qwen3-32B
Size=32B, Train=-
2026.06
11.4
Qwen3-235B
Size=235B, Train=-
2026.06
9.6
Feedback
Search any
task
Search any
task