Qwen 3.5 9B vs Qwen3 VL 8B (Reasoning)
| Benchmark | Qwen 3.5 9B | Qwen3 VL 8B (Reasoning) |
|---|---|---|
| Humanity's Last Exam | 14.9 | 3.8 |
| Terminal-Bench 4.0 | 0.5 | — |
| AutomationBench-AA | 1 | — |
| MMMU-Pro (vision) | 69.2 | 56.6 |
Specs
| Spec | Qwen 3.5 9B | Qwen3 VL 8B (Reasoning) |
|---|---|---|
| Input, per 1M | $0.08 | $0.18 |
| Output, per 1M | $0.13 | $2.09 |
| Cost per task? | $0.21 | — |
| Speed, tok/s | 60 | — |
| Context | 262K | 256K |
| Weights | Open | Open |
| Released | Mar 2026 | Oct 2025 |
| Memory (4-bit) | 4.8 GB | 4.4 GB |
| Licence | Apache-2.0 | Apache-2.0 |
| Commercial use | Allowed | Allowed |
| See images | ✓ | ✓ |
| Read PDFs | — | ? |
| Hear audio | — | — |
| Watch video | ✓ | — |
| Call tools | ✓ | ✓ |
| Force a tool call | Partial | ? |
| Return strict JSON | ✓ | Partial |
| Search the web | ? | ? |
| Run code | ? | ? |
| Use a computer | ? | ? |
What breaks when you switch
Qwen 3.5 9B → Qwen3 VL 8B (Reasoning)
Context: 262K → 256K
Qwen3 VL 8B (Reasoning) → Qwen 3.5 9B