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-oss-120b
gpt-oss-120b is an open-weight model from OpenAI, released Aug 5, 2025. It ranks #194 of 351 on the LMArena text leaderboard with a rating of 1366. It costs $0.15 per million input tokens and $0.60 per million output tokens, with a 128K-token context window.
- Developer
- OpenAI
- Released
- Aug 5, 2025
- Context window
- 128K
- Price in / out, per 1M tokens
- $0.15 / $0.60
- Weights
- Open · Apache 2.0
- Inputs
- Text
- Reasoning
- Yes
- Tool use
- Yes
- Hugging Face downloads, 30 days
- 2.9M
- Hugging Face likes
- 5.4K
The rating LMArena published at each update since Aug 7, 2025. Ratings move as votes come in and new models join.
Benchmarks
| Benchmark | Score bar | Accuracy | Rank | Cost / test |
|---|---|---|---|---|
| SWE-benchCoding | 33.60% | 84 / 85 | $0.17 | |
| LiveCodeBenchCoding | 83.23% | 51 / 143 | $0.15 / $0.6 | |
| MedQAMedicine | 91.36% | 38 / 92 | $0.15 / $0.6 | |
| GPQA DiamondReasoning | 78.54% | 74 / 138 | $0.15 / $0.6 | |
| MMLU-ProReasoning | 79.17% | 100 / 138 | $0.15 / $0.6 | |
| AIMEReasoning | 92.60% | 18 / 96 | $0.15 / $0.6 |
Vals AI, as of Oct 24, 2026.
LMArena, by category
| Leaderboard | Rating | Rank | Votes |
|---|---|---|---|
| TextLMArena | 1366 | 194 / 351 | 30.2K |
| CodingLMArena | 1379 | 195 / 346 | 6.4K |
| MathLMArena | 1389 | 180 / 339 | 1.8K |
| Creative writingLMArena | 1274 | 243 / 349 | 3.9K |
| Instruction followingLMArena | 1318 | 217 / 351 | 7.9K |
| Hard promptsLMArena | 1363 | 198 / 351 | 14.7K |
| Multi-turnLMArena | 1340 | 215 / 349 | 4.9K |
| Long queriesLMArena | 1319 | 230 / 330 | 6.6K |
| ExpertLMArena | 1356 | 196 / 305 | 1.4K |
| Legal and governmentIndustries | 1354 | 204 / 325 | 1.9K |
| Medicine and healthcareIndustries | 1388 | 174 / 325 | 1.6K |
| Business and financeIndustries | 1359 | 185 / 344 | 5.4K |
| ChineseLanguages | 1385 | 193 / 328 | 2.3K |
| SpanishLanguages | 1389 | 159 / 249 | 855 |
| GermanLanguages | 1353 | 169 / 261 | 673 |
| FrenchLanguages | 1369 | 177 / 252 | 460 |
| JapaneseLanguages | 1331 | 143 / 236 | 578 |
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-oss-120b
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-oss-120b?
gpt-oss-120b is made by OpenAI, founded 2015 and based in San Francisco.
How much does gpt-oss-120b cost?
$0.15 per million input tokens and $0.60 per million output tokens, at its provider’s list price.
What is gpt-oss-120b’s context window?
128K tokens (131,072).
How does gpt-oss-120b rank?
#194 of 351 on LMArena’s text leaderboard, rated 1366 (95% interval 1361–1370) from 30,207 votes, as of Oct 22, 2026.
Is gpt-oss-120b open source?
gpt-oss-120b has open weights under the Apache 2.0 license, downloadable from Hugging Face (openai/gpt-oss-120b).