Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
General Deep Research Tool Use on Xbench DeepSearch
Loading...
76
Success Rate
Gemini-3-Pro
21.92
35.96
50
64.04
Mar 10, 2026
Success Rate
Updated 1mo ago
Evaluation Results
Method
Method
Links
Success Rate
Gemini-3-Pro
Category=Frontier (≫8B...
2026.03
76
GPT-OSS-120B
Category=Frontier (≫8B...
2026.03
69.5
DeepSeek-V3.2-Exp
Category=Frontier (≫8B...
2026.03
67.2
Claude-4-Sonnet
Category=Frontier (≫8B...
2026.03
62.2
Kimi-K2-0905
Category=Frontier (≫8B...
2026.03
61
DIVE-8B (RL)
Category=Ours, Tempera...
2026.03
58.1
Gemini-2.5-Pro
Category=Frontier (≫8B...
2026.03
56
WebExplorer-8B
Category=8B Baselines,...
2026.03
53.7
DIVE-8B (SFT)
Category=Ours, Tempera...
2026.03
50.2
EnvScaler-8B
Category=8B Baselines,...
2026.03
45.7
SWE-Dev-8B
Category=8B Baselines,...
2026.03
31.6
Qwen3-8B (base)
Category=Ours, Tempera...
2026.03
24
Feedback
Search any
task
Search any
task