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-5.5
GPT-5.5 is a proprietary model from OpenAI, released Apr 24, 2026. It ranks #30 of 351 on the LMArena text leaderboard with a rating of 1472. It costs $5 per million input tokens and $30 per million output tokens, with a 1.1M-token context window.
- Developer
- OpenAI
- Released
- Apr 24, 2026
- Context window
- 1.1M
- Price in / out, per 1M tokens
- $5 / $30
- Weights
- Proprietary
- Inputs
- Files, Images, Text
- Reasoning
- Yes
- Tool use
- Yes
The rating LMArena published at each update since Apr 27, 2026. Ratings move as votes come in and new models join.
Benchmarks
| Benchmark | Score bar | Accuracy | Rank | Cost / test |
|---|---|---|---|---|
| SWE-benchCoding | 82.60% | 18 / 85 | $1.36 | |
| Vibe Code BenchCoding | 69.85% | 44 / 115 | $16.66 | |
| LiveCodeBenchCoding | 85.30% | 35 / 143 | $5 / $30 | |
| Tax Agent BenchFinance | 21.76% | 45 / 76 | $4.07 | |
| Legal Research BenchLaw | 40.38% | 32 / 85 | $7.40 | |
| MedCodeMedicine | 49.10% | 27 / 107 | $5 / $30 | |
| GPQA DiamondReasoning | 93.18% | 11 / 138 | $5 / $30 | |
| MMLU-ProReasoning | 88.14% | 21 / 138 | $5 / $30 | |
| MMMUReasoning | 88.27% | 9 / 93 | $5 / $30 |
Vals AI, as of Oct 24, 2026.
LMArena, by category
| Leaderboard | Rating | Rank | Votes |
|---|---|---|---|
| TextLMArena | 1472 | 30 / 351 | 69.4K |
| CodingLMArena | 1494 | 32 / 346 | 19.1K |
| MathLMArena | 1487 | 25 / 339 | 3.5K |
| Creative writingLMArena | 1455 | 29 / 349 | 13.2K |
| Instruction followingLMArena | 1479 | 22 / 351 | 24K |
| Hard promptsLMArena | 1489 | 22 / 351 | 45.5K |
| Multi-turnLMArena | 1476 | 28 / 349 | 11.8K |
| Long queriesLMArena | 1484 | 19 / 330 | 32K |
| ExpertLMArena | 1507 | 21 / 305 | 7.4K |
| Legal and governmentIndustries | 1491 | 18 / 325 | 5.6K |
| Medicine and healthcareIndustries | 1465 | 46 / 325 | 5.3K |
| Business and financeIndustries | 1478 | 16 / 344 | 13.7K |
| ChineseLanguages | 1534 | 15 / 328 | 4.5K |
| SpanishLanguages | 1468 | 33 / 249 | 1.9K |
| GermanLanguages | 1480 | 23 / 261 | 1.1K |
| FrenchLanguages | 1485 | 31 / 252 | 2.5K |
| JapaneseLanguages | 1499 | 9 / 236 | 908 |
| WebDevLMArena | 1513 | 59 / 124 | 15.6K |
| VisionLMArena | 1297 | 21 / 146 | 28.8K |
LMArena, CC BY 4.0, as of Oct 22, 2026. Where a model is rated at several effort levels, its best is shown (GPT-5.5 (High), GPT-5.5, GPT-5.5 (xHigh, Codex Harness), GPT-5.5 (High, Codex Harness)).
Compare GPT-5.5
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-5.5?
GPT-5.5 is made by OpenAI, founded 2015 and based in San Francisco.
How much does GPT-5.5 cost?
$5 per million input tokens and $30 per million output tokens, at its provider’s list price.
What is GPT-5.5’s context window?
1.1M tokens (1,050,000).
How does GPT-5.5 rank?
#30 of 351 on LMArena’s text leaderboard, rated 1472 (95% interval 1468–1475) from 69,375 votes, as of Oct 22, 2026.
Is GPT-5.5 open source?
No. GPT-5.5 is proprietary and served through its provider’s API.