Home/Models/GPT-5.1
OpenAI logo

GPT-5.1

by OpenAI · Released Nov 2025

Multimodal
57.0
avg score
Rank #83
Compare
Better than 64% of all models
Context
400K tokens (~200 books)
Input $/1M
$1.25
Output $/1M
$10.00
Type
multimodal
License
Proprietary
Benchmarks
24 tested
Data updated today
About

GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5. It uses adaptive reasoning...

Tested on 24 benchmarks with 49.6% average. Top scores: Chatbot Arena Elo — Overall (1438.5%), Chatbot Arena Elo — Coding (1338.8%), HELM — IFEval (93.5%).

Looking for similar performance at lower cost?
Qwen2.5 7B Instruct scores 57.4 (101% as good) at $0.04/1M input · 97% cheaper
Capabilities
coding
51.2
#64 globally
reasoning
55.1
#41 globally
math
44.6
#94 globally
knowledge
46.3
#117 globally
agentic
17.5
#24 globally
language
93.5
#4 globally
Benchmark Scores
Compare All
Tested on 24 benchmarks · Ranked across 7 categories
Score Distribution (all 233 models)
0255075100
▲ You are here
SWE-Bench verified

Real-world software engineering tasks from GitHub issues. Models must diagnose bugs and write patches that pass test suites. Human-verified subset of SWE-bench.

68.0
SWE-Bench Verified (Bash Only)

SWE-bench Verified solved using only bash commands, no specialized frameworks. Tests raw terminal-based problem solving.

66.0
WeirdML

Unusual and adversarial machine learning challenges. Tests robustness of reasoning about edge cases in ML systems.

60.8
HELM — WildBench

Stanford HELM WildBench evaluation. Tests reasoning on challenging real-world tasks.

86.3
ARC-AGI

Abstraction and Reasoning Corpus. Tests fluid intelligence through novel visual pattern recognition puzzles. Core measure of general intelligence.

72.8
SimpleBench

Deceptively simple questions that humans find easy but AI models often get wrong. Tests common sense and reasoning gaps.

43.8
OTIS Mock AIME 2024-2025

Mock AIME (American Invitational Mathematics Exam) problems from OTIS. Tests mathematical competition performance.

88.6
HELM — Omni-MATH

Stanford HELM evaluation of mathematical reasoning across diverse problem types.

46.4
FrontierMath-2025-02-28-Private

Original research-level math problems created by professional mathematicians. Problems are unpublished and cannot be memorized.

31.0
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Links
Documentation
Community
BenchGecko API
gpt-5-1
Specifications
  • Typemultimodal
  • Context400K tokens (~200 books)
  • ReleasedNov 2025
  • LicenseProprietary
  • StatusActive
  • Cost / Message~$0.013
Available On
OpenAI logoOpenAI$1.25
Share & Export
Tweet
GPT-5.1 is a proprietary multimodal AI model by OpenAI, released in November 2025. It has an average benchmark score of 57.0. Context window: 400K tokens.