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-4o
GPT-4o is a proprietary model from OpenAI, released Nov 20, 2024. It ranks #249 of 351 on the LMArena text leaderboard with a rating of 1300. It costs $2.50 per million input tokens and $10 per million output tokens, with a 125K-token context window.
- Developer
- OpenAI
- Released
- Nov 20, 2024
- Context window
- 125K
- Price in / out, per 1M tokens
- $2.50 / $10
- Weights
- Proprietary
- Inputs
- Text, Images, Files
- Reasoning
- No
- Tool use
- Yes
The rating LMArena published at each update since May 15, 2024. Ratings move as votes come in and new models join.
Benchmarks
| Benchmark | Score bar | Accuracy | Rank | Cost / test |
|---|---|---|---|---|
| LiveCodeBenchCoding | 43.44% | 124 / 143 | $2.5 / $10 | |
| MedQAMedicine | 88.16% | 54 / 92 | $2.5 / $10 | |
| GPQA DiamondReasoning | 50.25% | 123 / 138 | $5 / $15 | |
| MMLU-ProReasoning | 72.56% | 117 / 138 | $2.5 / $10 | |
| AIMEReasoning | 11.88% | 87 / 96 | $2.5 / $10 | |
| MMMUReasoning | 62.16% | 82 / 93 | $2.5 / $10 |
Vals AI, as of Oct 24, 2026.
LMArena, by category
| Leaderboard | Rating | Rank | Votes |
|---|---|---|---|
| TextLMArena | 1300 | 249 / 351 | 112.9K |
| CodingLMArena | 1297 | 261 / 346 | 19.5K |
| MathLMArena | 1285 | 250 / 339 | 6.8K |
| Creative writingLMArena | 1291 | 229 / 349 | 16.6K |
| Instruction followingLMArena | 1278 | 250 / 351 | 43.8K |
| Hard promptsLMArena | 1281 | 260 / 351 | 32.4K |
| Multi-turnLMArena | 1302 | 245 / 349 | 20.4K |
| Long queriesLMArena | 1288 | 260 / 330 | 14.9K |
| ExpertLMArena | 1250 | 256 / 305 | 5.9K |
| Legal and governmentIndustries | 1314 | 241 / 325 | 6.7K |
| Medicine and healthcareIndustries | 1278 | 259 / 325 | 6K |
| Business and financeIndustries | 1262 | 263 / 344 | 13.3K |
| ChineseLanguages | 1277 | 255 / 328 | 11.4K |
| SpanishLanguages | 1292 | 220 / 249 | 1.7K |
| GermanLanguages | 1283 | 207 / 261 | 3.6K |
| FrenchLanguages | 1304 | 215 / 252 | 1.4K |
| JapaneseLanguages | 1257 | 184 / 236 | 2.7K |
| VisionLMArena | 1137 | 124 / 146 | 23.3K |
LMArena, CC BY 4.0, as of Oct 22, 2026. Where a model is rated at several effort levels, its best is shown (GPT-4o (2024-05-13), GPT-4o (2024-08-06)).
Compare GPT-4o
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-4o?
GPT-4o is made by OpenAI, founded 2015 and based in San Francisco.
How much does GPT-4o cost?
$2.50 per million input tokens and $10 per million output tokens, at its provider’s list price.
What is GPT-4o’s context window?
125K tokens (128,000).
How does GPT-4o rank?
#249 of 351 on LMArena’s text leaderboard, rated 1300 (95% interval 1297–1304) from 112,881 votes, as of Oct 22, 2026.
Is GPT-4o open source?
No. GPT-4o is proprietary and served through its provider’s API.