Gemini 4 Argon
Claude Opus 5.5
Muse Wonder
MiMo-V2.6-Pro
Kimi K3
GLM-5.3
GPT-5.5
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
Qwen2.5-72B-Instruct
Qwen2.5-72B-Instruct is an open-weight model from Alibaba, released Sep 19, 2024. It ranks #284 of 351 on the LMArena text leaderboard with a rating of 1269. It costs $0.36 per million input tokens and $0.40 per million output tokens, with a 32K-token context window.
- Developer
- Alibaba Qwen
- Released
- Sep 19, 2024
- Context window
- 32K
- Price in / out, per 1M tokens
- $0.36 / $0.40
- Weights
- Open · Qwen
- Inputs
- Text
- Reasoning
- No
- Tool use
- Yes
- Hugging Face downloads, 30 days
- 221.4K
- Hugging Face likes
- 1K
The rating LMArena published at each update since Sep 27, 2024. Ratings move as votes come in and new models join.
LMArena, by category
| Leaderboard | Rating | Rank | Votes |
|---|---|---|---|
| TextLMArena | 1269 | 284 / 351 | 39.4K |
| CodingLMArena | 1292 | 264 / 346 | 6.7K |
| MathLMArena | 1283 | 253 / 339 | 5.4K |
| Creative writingLMArena | 1221 | 296 / 349 | 5.7K |
| Instruction followingLMArena | 1254 | 271 / 351 | 16.4K |
| Hard promptsLMArena | 1270 | 268 / 351 | 10.5K |
| Multi-turnLMArena | 1272 | 274 / 349 | 7.3K |
| Long queriesLMArena | 1281 | 266 / 330 | 6K |
| ExpertLMArena | 1245 | 262 / 305 | 2.4K |
| Legal and governmentIndustries | 1288 | 262 / 325 | 2.4K |
| Medicine and healthcareIndustries | 1258 | 272 / 325 | 2K |
| Business and financeIndustries | 1253 | 272 / 344 | 4.7K |
| ChineseLanguages | 1273 | 261 / 328 | 3.3K |
| SpanishLanguages | 1256 | 243 / 249 | 347 |
| GermanLanguages | 1234 | 242 / 261 | 926 |
| FrenchLanguages | 1280 | 230 / 252 | 340 |
| JapaneseLanguages | 1180 | 221 / 236 | 788 |
LMArena, CC BY 4.0, as of Oct 22, 2026. Where a model is rated at several effort levels, its best is shown.
Compare Qwen2.5-72B-Instruct
Alibaba Qwen
Alibaba Cloud’s Qwen team releases a broad family of open-weight models, from small to frontier scale. Founded 2023 (Qwen), based in Hangzhou. qwenlm.github.io
Questions
Who makes Qwen2.5-72B-Instruct?
Qwen2.5-72B-Instruct is made by Alibaba Qwen, founded 2023 (Qwen) and based in Hangzhou.
How much does Qwen2.5-72B-Instruct cost?
$0.36 per million input tokens and $0.40 per million output tokens, at its provider’s list price.
What is Qwen2.5-72B-Instruct’s context window?
32K tokens (32,768).
How does Qwen2.5-72B-Instruct rank?
#284 of 351 on LMArena’s text leaderboard, rated 1269 (95% interval 1265–1273) from 39,406 votes, as of Oct 22, 2026.
Is Qwen2.5-72B-Instruct open source?
Qwen2.5-72B-Instruct has open weights under the Qwen license, downloadable from Hugging Face (Qwen/Qwen2.5-72B-Instruct).