AL
Comparealibaba/qwen3-30b-a3b-instruct-2507
Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-quality instruction following, multilingual understanding, and...
- Context window
- 262K
- Input
- Text
- Output
- Text
- Released
- 2025-07-29
- Max output
- 32K
- Knowledge cutoff
- 2025-06-30
- Model parameters
- 31B
- Weights
- Open
- License
- apache-2.0
- Capabilities
- Open weight, Structured, Temperature, Tool call
Pricing
No official pricing available.
Performance
Overall capability
39.4/100
- Coding
- —
- Reasoning
- 36.6
- Professional work
- —
- Knowledge & language
- 29.4
| IFBench（Artificial Analysis）Qwen3 30B A3B 2507 Instruct | Knowledge & language | Artificial Analysis | 2026-11-05 | |
| AA-LCRQwen3 30B A3B 2507 Instruct | Knowledge & language | Artificial Analysis | 2026-11-05 | |
| CritPtQwen3 30B A3B 2507 Instruct | Reasoning | Artificial Analysis | 2026-11-05 | |
| Humanity’s Last ExamQwen3 30B A3B 2507 Instruct | Reasoning | Artificial Analysis | 2026-11-05 | |
| Arena Text Overall | Blind | LMArena | 2026-10-28 | |
| AA-OmniscienceQwen3 30B A3B 2507 Instruct | Knowledge & language | Artificial Analysis | 2026-10-27 |
Providers
No providers found
ModelRegistry · Catalog updated 2026-11-05