List your company

Long-horizon research task on BrowseComp-ZH

82.4ScoreSeed-2.0-Pro
40.851.662.473.2Jun 8, 2026

Evaluation results

MethodLinks
Seed-2.0-ProSize=-, Context management=true2026.0682.4
LongCat-Flash-Thinking-2601Size=560B-A27B, Context management=true2026.0677.7
GPT-5.2-ThinkingSize=-, Context management=false2026.0676.1
SearchSwarmSize=30B-A3B, Context management=true2026.0673.3
GLM-5.0Size=744B-A40B, Context management=true2026.0672.7
MiroThinker-1.7-miniSize=30B-A3B, Context management=true2026.0672.3
Step-3.5-FlashSize=196B-A11B, Context management=false2026.0666.9
Gemini-3.0-ProSize=-, Context management=false2026.0666.8
MiroThinker-1.5-miniSize=30B-A3B, Context management=true2026.0666.8
GLM-4.7Size=355B-A32B, Context management=true2026.0666.6
GPT-5Size=-, Context management=false2026.0665
DeepSeek V3.2Size=671B-A37B, Context management=true2026.0665
LongSeekerSize=30B-A3B, Context management=true2026.0662.5
Claude-4.5-OpusSize=-, Context management=false2026.0662.4
RedSearcherSize=30B-A3B, Context management=true2026.0658.2
Tongyi DeepResearchSize=30B-A3B, Context management=false2026.0646.7
Tongyi DR SwarmSize=30B-A3B, Context management=false2026.0646.7
Claude-4.5-SonnetSize=-, Context management=false2026.0642.4