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-4.1
GPT-4.1 is a proprietary model from OpenAI, released Apr 14, 2025. It ranks #174 of 351 on the LMArena text leaderboard with a rating of 1383. It costs $2 per million input tokens and $8 per million output tokens, with a 1M-token context window.
- Developer
- OpenAI
- Released
- Apr 14, 2025
- Context window
- 1M
- Price in / out, per 1M tokens
- $2 / $8
- Weights
- Proprietary
- Inputs
- Images, Text, Files
- Reasoning
- No
- 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 | 54.67% | 114 / 143 | $2 / $8 | |
| MedQAMedicine | 91.18% | 39 / 92 | $2 / $8 | |
| GPQA DiamondReasoning | 65.40% | 103 / 138 | $2 / $8 | |
| MMLU-ProReasoning | 80.50% | 89 / 138 | $2 / $8 | |
| AIMEReasoning | 39.58% | 70 / 96 | $2 / $8 | |
| MMMUReasoning | 72.39% | 65 / 93 | $2 / $8 |
Vals AI, as of Oct 24, 2026.
LMArena, by category
| Leaderboard | Rating | Rank | Votes |
|---|---|---|---|
| TextLMArena | 1383 | 174 / 351 | 50.3K |
| CodingLMArena | 1391 | 183 / 346 | 9.2K |
| MathLMArena | 1370 | 197 / 339 | 3.2K |
| Creative writingLMArena | 1363 | 153 / 349 | 6.7K |
| Instruction followingLMArena | 1367 | 173 / 351 | 13.3K |
| Hard promptsLMArena | 1384 | 175 / 351 | 22K |
| Multi-turnLMArena | 1398 | 156 / 349 | 8.7K |
| Long queriesLMArena | 1385 | 171 / 330 | 10K |
| ExpertLMArena | 1364 | 188 / 305 | 2.6K |
| Legal and governmentIndustries | 1400 | 158 / 325 | 3.2K |
| Medicine and healthcareIndustries | 1379 | 184 / 325 | 2.8K |
| Business and financeIndustries | 1369 | 177 / 344 | 8.2K |
| ChineseLanguages | 1382 | 196 / 328 | 3.3K |
| SpanishLanguages | 1376 | 171 / 249 | 1.1K |
| GermanLanguages | 1381 | 143 / 261 | 1.3K |
| FrenchLanguages | 1382 | 170 / 252 | 741 |
| JapaneseLanguages | 1319 | 150 / 236 | 1.1K |
| VisionLMArena | 1210 | 88 / 146 | 41K |
LMArena, CC BY 4.0, as of Oct 22, 2026. Where a model is rated at several effort levels, its best is shown.
Compare GPT-4.1
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-4.1?
GPT-4.1 is made by OpenAI, founded 2015 and based in San Francisco.
How much does GPT-4.1 cost?
$2 per million input tokens and $8 per million output tokens, at its provider’s list price.
What is GPT-4.1’s context window?
1M tokens (1,047,576).
How does GPT-4.1 rank?
#174 of 351 on LMArena’s text leaderboard, rated 1383 (95% interval 1379–1387) from 50,302 votes, as of Oct 22, 2026.
Is GPT-4.1 open source?
No. GPT-4.1 is proprietary and served through its provider’s API.