List your company

Deep Search on XBench-DS v1.0 (test)

68Success RateOpenAI o3*
19.43232.04144.6557.259Jun 10, 2026

Evaluation results

MethodLinks
OpenAI o3*2026.0668
OpenAI DeepResearch*2026.0666.7
Claude-4.5-Sonnet*2026.0666
TreeSeekerBackbone=gpt-5.22026.0656.3
Gemini-2.5-Pro*2026.0656
Kimi K2*2026.0654
WebSailor-32B*2026.0653.3
Gemini-DR*2026.0653
Claude-4-Sonnet-Thinking*2026.0653
Flash-SearcherBackbone=gpt-5.22026.0650.7
Grok3 DeepResearch*2026.0650
Doubao DeepResearch*2026.0650
Qwen3-235B-A22B-Instruct-2507*2026.0645.5
Tongyi-DeepSearch-30B-A3B2026.0645
IterResearchBackbone=gpt-5.22026.0644
WebDancer-32B*2026.0639
DeepSeek-R1*2026.0632.7
LATSBackbone=gpt-5.22026.0631
OpenAI GPT-5*2026.0630
Search-o1-32B*2026.0625
TreeSeekerBackbone=gpt-4.12026.0623
Flash-SearcherBackbone=gpt-4.12026.0621.3