Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
General Deep Research Tool Use on GAIA (success rate)
Loading...
80.3
Success Rate
Gemini-3-Pro
20.084
35.717
51.35
66.983
Mar 10, 2026
Success Rate
Updated 1mo ago
Evaluation Results
Method
Method
Links
Success Rate
Gemini-3-Pro
Category=Frontier (≫8B...
2026.03
80.3
GPT-OSS-120B
Category=Frontier (≫8B...
2026.03
66
Claude-4-Sonnet
Category=Frontier (≫8B...
2026.03
63.7
DIVE-8B (RL)
Category=Ours, Tempera...
2026.03
61.2
DeepSeek-V3.2-Exp
Category=Frontier (≫8B...
2026.03
61
Gemini-2.5-Pro
Category=Frontier (≫8B...
2026.03
60.2
Kimi-K2-0905
Category=Frontier (≫8B...
2026.03
60
WebExplorer-8B
Category=8B Baselines,...
2026.03
50
DIVE-8B (SFT)
Category=Ours, Tempera...
2026.03
49.3
EnvScaler-8B
Category=8B Baselines,...
2026.03
25.8
SWE-Dev-8B
Category=8B Baselines,...
2026.03
23.2
Qwen3-8B (base)
Category=Ours, Tempera...
2026.03
22.4
Feedback
Search any
task
Search any
task