Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Textual long-horizon complex reasoning on BrowseComp ZH
Loading...
82.4
Score
Doubao-2.0-Pro
4.296
24.573
44.85
65.127
Jun 13, 2026
Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Score
Doubao-2.0-Pro
Size=-, Train=-
2026.06
82.4
GPT-5.2
Size=-, Train=-
2026.06
76.1
MiroThinker-1.7
Size=235B, Train=Mid/S...
2026.06
75.3
GLM-5
Size=744B, Train=-
2026.06
72.7
MiroThinker-1.7-mini
Size=30B, Train=Mid/SF...
2026.06
72.3
Qwen3.5-397B
Size=397B, Train=-
2026.06
70.3
DeepSeek-V3.2
Size=671B, Train=-
2026.06
65
Gemini-3.1-Pro-Preview
Size=-, Train=-
2026.06
63.3
Kimi-K2.5
Size=1T, Train=-
2026.06
62.3
MiniMax-M2.7
Size=230B, Train=-
2026.06
56.4
REDSearcher
Size=30B, Train=Mid/SF...
2026.06
49.8
Claude-4.6-Sonnet-Thinking
Size=-, Train=-
2026.06
49.4
OpenSeeker-v1
Size=30B, Train=SFT
2026.06
48.4
S1-DeepResearch
Size=32B, Train=SFT
2026.06
48.4
Tongyi-DeepResearch
Size=30B, Train=Mid/SF...
2026.06
46.7
Qwen3-235B
Size=235B, Train=-
2026.06
13.5
Qwen3-32B
Size=32B, Train=-
2026.06
7.3
Feedback
Search any
task
Search any
task