Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Domain Deep Research Tool Use on FinSearchComp Global-T3
Loading...
52.4
Success Rate
Gemini-3-Pro
1.648
14.824
28
41.176
Mar 10, 2026
Success Rate
Updated 1mo ago
Evaluation Results
Method
Method
Links
Success Rate
Gemini-3-Pro
Category=Frontier (≫8B...
2026.03
52.4
DIVE-8B (RL)
Category=Ours, Tempera...
2026.03
37.3
Claude-4-Sonnet
Category=Frontier (≫8B...
2026.03
33.3
DIVE-8B (SFT)
Category=Ours, Tempera...
2026.03
33
Gemini-2.5-Pro
Category=Frontier (≫8B...
2026.03
27.4
DeepSeek-V3.2-Exp
Category=Frontier (≫8B...
2026.03
27.4
GPT-OSS-120B
Category=Frontier (≫8B...
2026.03
22
WebExplorer-8B
Category=8B Baselines,...
2026.03
18.1
EnvScaler-8B
Category=8B Baselines,...
2026.03
10.8
Kimi-K2-0905
Category=Frontier (≫8B...
2026.03
10.7
Qwen3-8B (base)
Category=Ours, Tempera...
2026.03
7.1
SWE-Dev-8B
Category=8B Baselines,...
2026.03
3.6
Feedback
Search any
task
Search any
task