Inference
EN
OpenAI

GPT-5.1

GPT-5.1 is a reasoning model from OpenAI. 25 benchmarks count toward its index, in 7 categories.

  • Closed weights
  • Reasoning
  • Input: image · text · file
  • Released 2025-11
RankedEnough results for an index.
IndexAll categories, out of 100.55.3±3.7Median 51.0
CoverageIndex weight that has results.95%
SpeedOutput tokens per second.50/sMedian 67/s
First tokenSeconds to the first output token.1.4 sMedian 1.3 s
Input / 1MUS dollars per 1M input tokens.$1.25batch $0.625Median $0.60
Output / 1MUS dollars per 1M output tokens.$10.00batch $5.00 Batch price per 1M output tokens.Median $2.55
ContextMaximum tokens in one request.400KMedian 262K
EloLMArena rating and rank.1422±4 #113Median 1422

Details

From OpenRouter
API IDThe model ID on OpenRouter.
openai/gpt-5.1
Max outputMaximum output tokens per request.
128K
Knowledge cutoffLast date of training data.
—
ToolsTool calls on OpenRouter.
Yes
JSON outputOutput follows a given JSON schema.
Yes
Cache read / 1MUS dollars per 1M cached tokens.
$0.125
WeightsLink to the published weights.
—
RetiresDate OpenRouter removes the model.
—

Where to run

APIs that serve this model.
3 providers
ProviderTypeMaker, cloud, host or router.InputOutputContext
DatabricksCloud$1.25$10.00400K
OpenRouterRouter$1.25$10.00400K
Snowflake CortexCloud$1.25$10.00272K

US dollars per 1M tokens, list price. From models.dev (opens in a new tab) (MIT).

Capabilities

Index per category, out of 100.
Out of 100
AgenticMulti-step tasks with tools.6 counted52.4117 / 218
CodingCode writing and repair.4 counted53.5110 / 209
ReasoningLogic problems and puzzles.4 counted56.476 / 227
MultimodalTasks with images and text.1 counted58.4—
KnowledgeFacts and expert knowledge.5 counted57.278 / 268
MultilingualTasks in many languages.None counted——
InstructionTasks with strict prompt rules.1 counted57.1—
MathMath problems.4 counted57.554 / 168

Results

25 counted
BenchmarkThe benchmark name.ResultThe score from the source.PlacePlace among results on this benchmark.
LiveCodeBenchCoding86.5% ±1.022 / 142
AIMEMath93.3% ±0.615 / 95
Artificial Analysis Long Context ReasoningReasoning80.0%43 / 217
Artificial Analysis IFBenchInstruction72.9%33 / 146
FrontierMath-2025-02-28-PrivateMath31.0% ±2.718 / 69
GPQA diamond · Epoch AIKnowledge87.6% ±1.961 / 217
Artificial Analysis GPQA DiamondKnowledge87.3%58 / 199
SWE-bench Verified · SWE-bench/experimentsCoding66.0%19 / 65
Terminal-Bench 1.0Agentic47.5% ±5.614 / 47
GPQA Diamond · Vals AIKnowledge86.6% ±1.741 / 135
FrontierMath-Tier-4-2025-07-01-PrivateMath12.5% ±4.817 / 55
MMLU ProKnowledge86.4% ±0.342 / 135
OTIS Mock AIME 2024-2025Math88.6% ±4.067 / 200
IOI v1Coding21.5% ±7.321 / 61
MMMU ProMultimodal83.2% ±0.933 / 92
Terminal-Bench 2.0 · Vals AIAgentic44.9% ±5.324 / 66
Chess PuzzlesReasoning42.0% ±5.033 / 90
Artificial Analysis Omniscience AccuracyKnowledge37.7%62 / 164
SimpleQA VerifiedKnowledge48.0% ±1.635 / 91
Artificial Analysis Humanity's Last ExamKnowledge28.5%87 / 222
Critical Physics TasksReasoning4.9%84 / 214
Artificial Analysis LiveCodeBenchCoding86.8%5 / 12
Artificial Analysis MMMU-ProMultimodal75.5%48 / 113
τ²-Bench Tool-Agent-User EvaluationAgentic81.9%66 / 149
Artificial Analysis MMLU-ProKnowledge87.0%7 / 15
GDPval-AA normalizedAgentic16.3%85 / 133
Terminal-Bench HardAgentic45.5%15 / 23
Gert Labs Composite Game BenchmarkAgentic41.2%35 / 52
Vibe Code Bench v1.1Coding24.6% ±4.385 / 123
Mystery Game PuzzlesReasoning16.0% ±3.756 / 80
SWE-benchCoding69.8% ±2.164 / 87
SWE-Bench verified · Epoch AICoding66.9% ±2.125 / 32
MedQAHealthcare96.4% ±0.22 / 95
CaseLaw v2Legal73.4% ±0.82 / 53
MedCodeHealthcare52.7% ±2.213 / 106
MedScribeHealthcare88.1% ±1.914 / 109
LegalBenchLegal85.7% ±0.420 / 149
MGSMMultilingual93.0% ±1.511 / 74
TaxEval v2Finance74.9% ±0.926 / 143
Finance Agent v1.1Finance55.3% ±2.813 / 51
CorpFin v2Finance63.8% ±0.939 / 131
MortgageTaxFinance61.4% ±0.960 / 97
Artificial Analysis AIME 2025Math94.0%—
Artificial Analysis Global-MMLU-LiteMultilingual90.6%—

Sources

BenchLMCC BY-NC 4.0OpenRouterTerms restrict reuseVals AINo licence statedEpoch AICC BYSWE-bench teamNo licence statedmodels.devMIT

History

5 releases
Index56.2 → 55.3
23 Oct 202612 Nov 2026
Output / 1M$10.00 → $10.00
23 Oct 202612 Nov 2026

Questions

How much does GPT-5.1 cost?
$1.25 per 1M input tokens, $10.00 per 1M output tokens.
How good is GPT-5.1?
Its index is 55.3 out of 100. That is place 99 of 283 ranked models.
What is GPT-5.1 best at?
Knowledge: 57.2 out of 100, place 78 of 268.
How fast is GPT-5.1?
50 output tokens per second, 1.4 s to the first token.
What is the context window of GPT-5.1?
400K tokens.
Is GPT-5.1 open source?
No. Its weights are not published.
When was GPT-5.1 released?
November 2025.

Badge

GPT-5.1 on Inference360: place 99 of 283, index 55.3
HTML
<a href="https://inference360.ai/models/gpt-5-1"><img src="https://inference360.ai/badges/gpt-5-1.svg" alt="GPT-5.1 on Inference360: place 99 of 283, index 55.3" height="20"></a>
Markdown
[![GPT-5.1 on Inference360: place 99 of 283, index 55.3](https://inference360.ai/badges/gpt-5-1.svg)](https://inference360.ai/models/gpt-5-1)

Compare with

Step 3.7 Flash55.3Qwen3.5 397B (Reasoning)55.3Inkling-Small55.1GPT-555.0Grok 4.20 (Reasoning)55.5

Lower price

dots3-note Preview63.4 · FreeApodex 1.1 Mini55.7 · FreeGLM-5.3-Flash63.1 · $0.078/1M

More from OpenAI

All models
GPT-5.1-Codex52.9GPT-5.1 Codex MiniUnrankedGPT-5.1-Codex-Max53.8GPT OSS Safeguard 20BUnrankedGPT-5 Image MiniUnranked