Private AI
Gemini 3.1 Pro preview is built for tasks where simple answers are not enough. Stronger core reasoning for complex coding, math, and long-context workflows, with multimodal support and a reported 77.1% verified score on ARC-AGI-2. NOTE: Inputs > 200k tokens are charged at 2x input and 1.5x output rates.
Added Feb 19, 2026
Context Window
1.0M
Max Output
65.5K
Avg output tokens (7d)
1.6K tokens
Input Price (Auto)
$2.00/1M
Output Price (Auto)
$12.00/1M
Cache Read (Auto)
$0.20/1M
Capabilities
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
46.5
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
Coding Index
68.8
Agentic Index
21.4
GPQA Diamond
Graduate-level scientific reasoning
94.1%
Better than 99% of models compared
HLE
Humanity's Last Exam
44.7%
Better than 98% of models compared
IFBench
Instruction-following benchmark
77.1%
Better than 96% of models compared
T²-Bench Telecom
Conversational AI agents in dual-control scenarios
95.6%
Better than 95% of models compared
AA-LCR
Long context reasoning evaluation
72.7%
Better than 96% of models compared
GDPval-AA
Economically valuable tasks
23.2%
CritPt
Research-level physics reasoning
17.7%
SciCode
Python programming for scientific computing
58.9%
Better than 99% of models compared
Terminal-Bench Hard
Agentic coding and terminal use
53.8%
AA-Omniscience Accuracy
Proportion of correctly answered questions
55.2%
AA-Omniscience Hallucination Rate
Rate of incorrect answers among non-correct responses
49.9%
Last updated Jul 31, 2026
Artificial AnalysisBetter than 96% of models compared
