Gemini 4 Argon
Claude Opus 5.5
Muse Wonder
MiMo-V2.6-Pro
Qwen3.8-Max
Kimi K3
GLM-5.3
ERNIE 5.1
DeepSeek-V4.1-Flash-20260910
Grok 4.20 Beta
amazon-nova-experimental-chat
Dola Seed 2.0 Pro
NVIDIA-Nemotron-3-Ultra-550B-A55B
Gemma 4 31B
Step 5 Preview
GPT-5.1
GPT-5.1 is a proprietary model from OpenAI, released Nov 13, 2025. It ranks #68 of 351 on the LMArena text leaderboard with a rating of 1443. It costs $1.25 per million input tokens and $10 per million output tokens, with a 400K-token context window.
- Developer
- OpenAI
- Released
- Nov 13, 2025
- Context window
- 400K
- Price in / out, per 1M tokens
- $1.25 / $10
- Weights
- Proprietary
- Inputs
- Images, Text, Files
- Reasoning
- Yes
- Tool use
- Yes
The rating LMArena published at each update since Nov 16, 2025. Ratings move as votes come in and new models join.
Benchmarks
| Benchmark | Score bar | Accuracy | Rank | Cost / test |
|---|---|---|---|---|
| SWE-benchCoding | 69.80% | 62 / 85 | $0.71 | |
| Vibe Code BenchCoding | 24.61% | 77 / 115 | $2.57 | |
| LiveCodeBenchCoding | 86.49% | 22 / 143 | $1.25 / $10 | |
| MedCodeMedicine | 52.73% | 13 / 107 | $1.25 / $10 | |
| MedQAMedicine | 96.38% | 2 / 92 | $1.25 / $10 | |
| GPQA DiamondReasoning | 86.62% | 41 / 138 | $1.25 / $10 | |
| MMLU-ProReasoning | 86.38% | 42 / 138 | $1.25 / $10 | |
| AIMEReasoning | 93.33% | 15 / 96 | $1.25 / $10 | |
| MMMUReasoning | 83.18% | 33 / 93 | $1.25 / $10 |
Vals AI, as of Oct 24, 2026.
LMArena, by category
| Leaderboard | Rating | Rank | Votes |
|---|---|---|---|
| TextLMArena | 1443 | 68 / 351 | 41.6K |
| CodingLMArena | 1453 | 97 / 346 | 8.4K |
| MathLMArena | 1446 | 76 / 339 | 2.6K |
| Creative writingLMArena | 1427 | 62 / 349 | 6.2K |
| Instruction followingLMArena | 1443 | 57 / 351 | 11.2K |
| Hard promptsLMArena | 1457 | 64 / 351 | 22.4K |
| Multi-turnLMArena | 1450 | 67 / 349 | 7.2K |
| Long queriesLMArena | 1448 | 66 / 330 | 10.9K |
| ExpertLMArena | 1470 | 60 / 305 | 2.6K |
| Legal and governmentIndustries | 1459 | 54 / 325 | 3.1K |
| Medicine and healthcareIndustries | 1457 | 56 / 325 | 2.6K |
| Business and financeIndustries | 1431 | 77 / 344 | 7.7K |
| ChineseLanguages | 1495 | 57 / 328 | 3.4K |
| SpanishLanguages | 1433 | 95 / 249 | 1.2K |
| GermanLanguages | 1438 | 76 / 261 | 718 |
| FrenchLanguages | 1450 | 86 / 252 | 944 |
| JapaneseLanguages | 1454 | 29 / 236 | 459 |
| WebDevLMArena | 1396 | 102 / 124 | 4.9K |
| VisionLMArena | 1250 | 64 / 146 | 9.8K |
LMArena, CC BY 4.0, as of Oct 22, 2026. Where a model is rated at several effort levels, its best is shown (GPT-5.1 (High), GPT-5.1, GPT-5.1 (Medium)).
Compare GPT-5.1
OpenAI
The lab behind GPT and ChatGPT, which brought large language models to hundreds of millions of people. Founded 2015, based in San Francisco. openai.com
Questions
Who makes GPT-5.1?
GPT-5.1 is made by OpenAI, founded 2015 and based in San Francisco.
How much does GPT-5.1 cost?
$1.25 per million input tokens and $10 per million output tokens, at its provider’s list price.
What is GPT-5.1’s context window?
400K tokens (400,000).
How does GPT-5.1 rank?
#68 of 351 on LMArena’s text leaderboard, rated 1443 (95% interval 1439–1446) from 41,646 votes, as of Oct 22, 2026.
Is GPT-5.1 open source?
No. GPT-5.1 is proprietary and served through its provider’s API.