Private AI
Version-pinned snapshot of GPT-5.1 from the November 13, 2025 release. Use this when audits or regulated workflows require deterministic behavior.
Context Window
1.0M
Max Output
32.8K
Input Price (Auto)
$1.25/1M
Output Price (Auto)
$10.00/1M
Cache Read (Auto)
$0.13/1M
Capabilities
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
20.4
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…
GPQA Diamond
Graduate-level scientific reasoning
64.3%
Better than 43% of models compared
HLE
Humanity's Last Exam
5.2%
Better than 37% of models compared
IFBench
Instruction-following benchmark
43.2%
Better than 47% of models compared
T²-Bench Telecom
Conversational AI agents in dual-control scenarios
46.5%
Better than 50% of models compared
AA-LCR
Long context reasoning evaluation
44.0%
Better than 53% of models compared
CritPt
Research-level physics reasoning
0.0%
SciCode
Python programming for scientific computing
36.5%
Better than 59% of models compared
Terminal-Bench Hard
Agentic coding and terminal use
22.7%
AIME 2025
American Invitational Mathematics Examination 2025
38.0%
Better than 39% of models compared
MMLU-Pro
Professional and academic subject knowledge
80.1%
Better than 68% of models compared
AA-Omniscience Accuracy
Proportion of correctly answered questions
29.1%
Last updated Aug 4, 2026
Artificial AnalysisBetter than 62% of models compared
LiveCodeBench
Contamination-free coding benchmark
49.4%
Better than 56% of models compared
AA-Omniscience Hallucination Rate
Rate of incorrect answers among non-correct responses
90.2%
