TAU2
Measured May 29, 2026Source
Score
0.87
Models13 0 
Gemini 3 Deep Think
GoogleGoogleUnited States
Gemini 3 Deep Think is a model from Google's Gemini series, optimized for deep reasoning and complex problem-solving tasks. It leverages advanced thinking processes to handle intricate queries and is part of the multimodal Gemini family.
ReasoningLong contextMultimodal
Input / 1M tokens
$0.00Output / 1M tokens
$0.00Supported plans
0Benchmark history
Evaluations
Terminalbench Hard
Measured May 29, 2026Source
Score
0.42
Lcr
Measured May 29, 2026Source
Score
0.71
Ifbench
Measured May 29, 2026Source
Score
0.78
Aime 25
Measured May 29, 2026Source
Score
0.97
Scicode
Measured May 29, 2026Source
Score
0.56
Livecodebench
Measured May 29, 2026Source
Score
0.92
Hle
Measured May 29, 2026Source
Score
0.37
Gpqa
Measured May 29, 2026Source
Score
0.91
Mmlu Pro
Measured May 29, 2026Source
Score
0.9
Artificial Analysis Math Index
Measured May 29, 2026Source
Score
97
Artificial Analysis Coding Index
Measured May 29, 2026Source
Score
46.5
Artificial Analysis Intelligence Index
Measured May 29, 2026Source
Score
48.4
Plan availability
Products and plans that support this model
No products or plans have been linked to this model yet.
User ratings
Loading ratings...
Discussion
Thinking... Make sure you are connected to GitHub server