Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Long-horizon research task on BrowseComp-ZH
Loading...
82.4
Score
Seed-2.0-Pro
40.8
51.6
62.4
73.2
Jun 8, 2026
Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Score
Seed-2.0-Pro
Size=-, Context manage...
2026.06
82.4
LongCat-Flash-Thinking-2601
Size=560B-A27B, Contex...
2026.06
77.7
GPT-5.2-Thinking
Size=-, Context manage...
2026.06
76.1
SearchSwarm
Size=30B-A3B, Context...
2026.06
73.3
GLM-5.0
Size=744B-A40B, Contex...
2026.06
72.7
MiroThinker-1.7-mini
Size=30B-A3B, Context...
2026.06
72.3
Step-3.5-Flash
Size=196B-A11B, Contex...
2026.06
66.9
Gemini-3.0-Pro
Size=-, Context manage...
2026.06
66.8
MiroThinker-1.5-mini
Size=30B-A3B, Context...
2026.06
66.8
GLM-4.7
Size=355B-A32B, Contex...
2026.06
66.6
GPT-5
Size=-, Context manage...
2026.06
65
DeepSeek V3.2
Size=671B-A37B, Contex...
2026.06
65
LongSeeker
Size=30B-A3B, Context...
2026.06
62.5
Claude-4.5-Opus
Size=-, Context manage...
2026.06
62.4
RedSearcher
Size=30B-A3B, Context...
2026.06
58.2
Tongyi DeepResearch
Size=30B-A3B, Context...
2026.06
46.7
Tongyi DR Swarm
Size=30B-A3B, Context...
2026.06
46.7
Claude-4.5-Sonnet
Size=-, Context manage...
2026.06
42.4
Feedback
Search any
task
Search any
task