AL
Compare- Context window
- 262K
- Input
- Image · Text
- Output
- Text
- Released
- 2026-02-15
- Max output
- 66K
- Knowledge cutoff
- 2025-04
- Model parameters
- 403B
- Weights
- Open
- License
- apache-2.0
- Capabilities
- Attachments, Open weight, Reasoning, Structured, Temperature, Tool call
No official pricing available.
Performance
Overall capability
45.3/100
- Coding
- 42.5
- Reasoning
- 42.3
- Professional work
- 36.2
- Knowledge & language
- 57.3
| MLCR-AA(Artificial Analysis)Qwen3.5 397B A17B (Reasoning) | Knowledge & language | Artificial Analysis | 2026-11-05 | |
| Terminal-Bench 4.0 (AA rerun)Qwen3.5 397B A17B (Reasoning) | Coding | Artificial Analysis | 2026-11-05 | |
| Humanity’s Last ExamQwen3.5 397B A17B (Reasoning) | Reasoning | Artificial Analysis | 2026-11-05 | |
| AutomationBench-AAQwen3.5 397B A17B (Reasoning) | Professional work | Artificial Analysis | 2026-11-05 | |
| BullshitBench v2 | Knowledge & language | BullshitBench | 2026-11-05 | |
| AA-Briefcase | Professional work | Artificial Analysis | 2026-11-05 | |
| GDPval-AA | Professional work | Artificial Analysis | 2026-11-05 | |
| FrontierMath v2 Tiers 1–3 | Reasoning | Epoch AI | 2026-11-05 |
Providers
No providers found
ModelRegistry · Catalog updated 2026-11-05