GPT 5.1

Model

Compare Models

GPT 5.1

Release Date: Nov 13, 2025

Developer OpenAI 🇺🇸

Context Window 400k

Max Output Tokens 128k

Token Costs (in/out) $1.25/10.00

Weights Private

Input Modalities

Accuracy

64.96 %

Avg. Cost (In/Out)

$ 1.25 / $ 10.00

Latency

6 min 42 s

BenchmarksAccuracyRankings

MedCode

0.0%

±2.15

10/86

MedScribe

0.0%

±1.94

5/87

MortgageTax

0.0%

±0.93

59/96

SAGE

0.0%

±3.16

40/77

TaxEval v2

0.0%

±0.85

25/141

Vibe Code Bench v1.1

0.0%

±4.25

50/86

GPQA Diamond

0.0%

±1.71

39/135

IOI

0.0%

±7.34

21/62

LiveCodeBench

0.0%

±0.98

20/140

LegalBench

0.0%

±0.40

15/139

MMLU Pro

0.0%

±0.34

40/135

MMMU

0.0%

±0.90

30/90

SWE-bench

0.0%

±2.06

63/86

Proprietary BenchmarksAcademic BenchmarksIndustry Partners

View Hyperparameter Settings

Default Provider : OpenAI

Temperature: Default

Top P: Default

Top K: Default

Max Output Tokens: 128,000

Reasoning Effort: high

Updates

Nov 14, 2025

GPT 5.1 takes first place on Finance Agent!

We just evaluated GPT 5.1 on all benchmarks. Our findings are below:

GPT 5.1 takes second place on the Vals Index, behind the reigning champion, Claude Sonnet 4.5 (Thinking).
GPT 5.1 shines on agent benchmarks, placing first on our Finance Agent Benchmark.
GPT 5.1 also excels at competitive coding, placing second on both LiveCodeBench and our IOI Benchmark.
GPT 5.1 performs comparably to GPT 5, but much more cheaply and quickly - we consider it a clear leader on Pareto frontier between performance and cost.