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
Qwen3-30B-A3B-Instruct
Qwen3-30B-A3B-Instruct is an open-weight model from Alibaba, released Jul 29, 2025. It ranks #172 of 351 on the LMArena text leaderboard with a rating of 1384. It costs $0.09 per million input tokens and $0.30 per million output tokens, with a 256K-token context window.
- Developer
- Alibaba Qwen
- Released
- Jul 29, 2025
- Context window
- 256K
- Price in / out, per 1M tokens
- $0.09 / $0.30
- Weights
- Open · Apache 2.0
- Inputs
- Text
- Reasoning
- No
- Tool use
- Yes
- Hugging Face downloads, 30 days
- 1.1M
- Hugging Face likes
- 850
The rating LMArena published at each update since Aug 4, 2025. Ratings move as votes come in and new models join.
LMArena, by category
| Leaderboard | Rating | Rank | Votes |
|---|---|---|---|
| TextLMArena | 1384 | 172 / 351 | 23.3K |
| CodingLMArena | 1416 | 154 / 346 | 4.6K |
| MathLMArena | 1395 | 173 / 339 | 1.4K |
| Creative writingLMArena | 1317 | 206 / 349 | 3K |
| Instruction followingLMArena | 1363 | 177 / 351 | 6K |
| Hard promptsLMArena | 1398 | 169 / 351 | 11K |
| Multi-turnLMArena | 1379 | 178 / 349 | 3.9K |
| Long queriesLMArena | 1378 | 175 / 330 | 4.9K |
| ExpertLMArena | 1396 | 163 / 305 | 1.2K |
| Legal and governmentIndustries | 1387 | 172 / 325 | 1.5K |
| Medicine and healthcareIndustries | 1392 | 167 / 325 | 1.3K |
| Business and financeIndustries | 1389 | 158 / 344 | 4.1K |
| ChineseLanguages | 1433 | 147 / 328 | 1.8K |
| SpanishLanguages | 1404 | 141 / 249 | 715 |
| GermanLanguages | 1379 | 144 / 261 | 522 |
| FrenchLanguages | 1419 | 135 / 252 | 336 |
| JapaneseLanguages | 1338 | 137 / 236 | 767 |
LMArena, CC BY 4.0, as of Oct 22, 2026. Where a model is rated at several effort levels, its best is shown.
Compare Qwen3-30B-A3B-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 Qwen3-30B-A3B-Instruct?
Qwen3-30B-A3B-Instruct is made by Alibaba Qwen, founded 2023 (Qwen) and based in Hangzhou.
How much does Qwen3-30B-A3B-Instruct cost?
$0.09 per million input tokens and $0.30 per million output tokens, at its provider’s list price.
What is Qwen3-30B-A3B-Instruct’s context window?
256K tokens (262,144).
How does Qwen3-30B-A3B-Instruct rank?
#172 of 351 on LMArena’s text leaderboard, rated 1384 (95% interval 1379–1389) from 23,306 votes, as of Oct 22, 2026.
Is Qwen3-30B-A3B-Instruct open source?
Qwen3-30B-A3B-Instruct has open weights under the Apache 2.0 license, downloadable from Hugging Face (Qwen/Qwen3-30B-A3B-Instruct-2507).