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
o4-mini
o4-mini is a proprietary model from OpenAI, released Apr 16, 2025. It ranks #206 of 351 on the LMArena text leaderboard with a rating of 1353. It costs $1.10 per million input tokens and $4.40 per million output tokens, with a 200K-token context window.
- Developer
- OpenAI
- Released
- Apr 16, 2025
- Context window
- 200K
- Price in / out, per 1M tokens
- $1.10 / $4.40
- Weights
- Proprietary
- Inputs
- Images, Text, Files
- Reasoning
- Yes
- Tool use
- Yes
The rating LMArena published at each update since Apr 23, 2025. Ratings move as votes come in and new models join.
Benchmarks
| Benchmark | Score bar | Accuracy | Rank | Cost / test |
|---|---|---|---|---|
| LiveCodeBenchCoding | 82.21% | 55 / 143 | $1.1 / $4.4 | |
| MedCodeMedicine | 33.79% | 84 / 107 | $1.1 / $4.4 | |
| MedQAMedicine | 96.02% | 9 / 92 | $1.1 / $4.4 | |
| GPQA DiamondReasoning | 74.50% | 85 / 138 | $1.1 / $4.4 | |
| MMLU-ProReasoning | 80.56% | 88 / 138 | $1.1 / $4.4 | |
| AIMEReasoning | 83.67% | 41 / 96 | $1.1 / $4.4 | |
| MMMUReasoning | 79.67% | 46 / 93 | $1.1 / $4.4 |
Vals AI, as of Oct 24, 2026.
LMArena, by category
| Leaderboard | Rating | Rank | Votes |
|---|---|---|---|
| TextLMArena | 1353 | 206 / 351 | 44.9K |
| CodingLMArena | 1368 | 208 / 346 | 8.6K |
| MathLMArena | 1389 | 178 / 339 | 2.9K |
| Creative writingLMArena | 1294 | 225 / 349 | 5.8K |
| Instruction followingLMArena | 1320 | 215 / 351 | 11.9K |
| Hard promptsLMArena | 1350 | 211 / 351 | 19.4K |
| Multi-turnLMArena | 1350 | 204 / 349 | 7.7K |
| Long queriesLMArena | 1315 | 236 / 330 | 8.6K |
| ExpertLMArena | 1343 | 204 / 305 | 2.3K |
| Legal and governmentIndustries | 1350 | 207 / 325 | 2.7K |
| Medicine and healthcareIndustries | 1362 | 201 / 325 | 2.5K |
| Business and financeIndustries | 1325 | 219 / 344 | 7K |
| ChineseLanguages | 1354 | 217 / 328 | 3K |
| SpanishLanguages | 1346 | 199 / 249 | 996 |
| GermanLanguages | 1336 | 184 / 261 | 1.2K |
| FrenchLanguages | 1364 | 183 / 252 | 614 |
| JapaneseLanguages | 1308 | 157 / 236 | 1.1K |
| VisionLMArena | 1194 | 98 / 146 | 41.3K |
LMArena, CC BY 4.0, as of Oct 22, 2026. Where a model is rated at several effort levels, its best is shown.
Compare o4-mini
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 o4-mini?
o4-mini is made by OpenAI, founded 2015 and based in San Francisco.
How much does o4-mini cost?
$1.10 per million input tokens and $4.40 per million output tokens, at its provider’s list price.
What is o4-mini’s context window?
200K tokens (200,000).
How does o4-mini rank?
#206 of 351 on LMArena’s text leaderboard, rated 1353 (95% interval 1349–1357) from 44,851 votes, as of Oct 22, 2026.
Is o4-mini open source?
No. o4-mini is proprietary and served through its provider’s API.