Google's newest model, outperforming even Gemini 1.5 Pro, now with a thinking mode enabled similar to the o1 series of OpenAI.
Added Jan 21, 2025
Context Window
1.0M
Max Output
8.2K
Input Price (Auto)
$0.31/1M
Output Price (Auto)
$1.00/1M
Cache Read (Auto)
$0.076/1M
Capabilities
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
18.5
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
Coding Index
13.6
GPQA Diamond
Graduate-level scientific reasoning
62.3%
Better than 51% of models compared
HLE
Humanity's Last Exam
5.3%
Better than 49% of models compared
IFBench
Instruction-following benchmark
40.2%
Better than 47% of models compared
T²-Bench Telecom
Conversational AI agents in dual-control scenarios
29.5%
Better than 43% of models compared
AA-LCR
Long context reasoning evaluation
28.3%
Better than 47% of models compared
SciCode
Python programming for scientific computing
33.3%
Better than 60% of models compared
Terminal-Bench Hard
Agentic coding and terminal use
3.8%
Better than 28% of models compared
AIME 2025
American Invitational Mathematics Examination 2025
21.7%
Better than 23% of models compared
AIME
American Invitational Mathematics Examination
33.0%
Better than 61% of models compared
MMLU-Pro
Professional and academic subject knowledge
77.9%
Better than 59% of models compared
Last updated May 15, 2026
Artificial AnalysisLiveCodeBench
Contamination-free coding benchmark
33.4%
Better than 40% of models compared
Math-500
Diverse mathematical problem solving benchmark
93.0%
Better than 71% of models compared
