Qwen 3.5 27B vs Qwen3.8 27B
| Benchmark | Qwen 3.5 27B | Qwen 27B |
|---|---|---|
| Humanity's Last Exam | 23.9 | 14.1 |
| Terminal-Bench 4.0 | — | 5.1 |
| AutomationBench-AA | — | 40.3 |
| MMMU-Pro (vision) | 75 | 74.2 |
Specs
| Spec | Qwen 3.5 27B | Qwen 27B |
|---|---|---|
| Input, per 1M | $0.30 | $0.42 |
| Output, per 1M | $2.40 | $2.55 |
| Cost per task? | — | $1.27 |
| Speed, tok/s | 77 | 46 |
| Context | 262K | 262K |
| Weights | Open | Open |
| Released | Feb 2026 | Aug 2026 |
| Memory (4-bit) | 17 GB | 17 GB |
| Licence | Apache-2.0 | Apache-2.0 |
| Commercial use | Allowed | Allowed |
| See images | ✓ | ✓ |
| Read PDFs | — | Partial |
| Hear audio | — | — |
| Watch video | ✓ | ✓ |
| Call tools | ✓ | ✓ |
| Force a tool call | Partial | Partial |
| Return strict JSON | ✓ | ✓ |
| Search the web | ? | ? |
| Run code | ? | ? |
| Use a computer | ? | ? |
What breaks when you switch
Qwen 3.5 27B → Qwen 27B
max_tokens range · QwenCloud›
With thinking enabled, max_tokens outside 1–32768 returns HTTP 400; use max_completion_tokens to budget reasoning plus answer without that cap.
Static YaRN affects shorter texts · Self-hosted›
Static YaRN can hurt short-text performance; change rope_parameters only when longer contexts are required.
tool_choice only supports auto or none · QwenCloud›
With thinking enabled, tool_choice supports only auto or none.
Include the word JSON · QwenCloud›
JSON Object mode requires the word JSON in a system or user message; otherwise the API returns an error.
Agent search_strategy not supported · QwenCloud / Chat Completions›
Chat Completions does not support Qwen3.8 agent search_strategy; use the Responses web_search tool for multi-turn retrieval.
Qwen 27B → Qwen 3.5 27B
Nothing known.