Qwen3.8 Max (0902) vs Qwen3.8 Max
Terminal-Bench 4.0 Terminal-Bench 4.0 · source setting 2: Agents use a terminal to complete executable coding, system administration and research tasks in the 4.0 suite
Qwen Max (0902)38.9
Qwen Max18.7
WebDev Arena WebDev Arena: Human pairwise preferences in the stated webdev vote pool
Qwen Max (0902) · max1,674
Qwen Max · max1,672
SciCode SciCode: Writing code for real scientific computing problems (physics, biology, math)
Qwen Max (0902)52.1
Qwen Max53.2
DeepSWE 1.1 DeepSWE 1.1: Agents change repository code to resolve software engineering tasks under the stated DeepSWE edition
Qwen Max (0902)—
Qwen Max · xhigh57.5
FrontierCode 1.1 FrontierCode 1.1: Agents implement changes in real repositories, graded against maintainer-defined requirements
Qwen Max (0902)43.2
Qwen Max—
Terminal-Bench Science 0.1 Terminal-Bench Science 0.1: Agents complete expert-authored research workflows across five scientific domains in a terminal
Qwen Max (0902)11.9
Qwen Max—
| Benchmark | Qwen Max (0902) | Qwen Max |
|---|---|---|
| Terminal-Bench 4.0 | 38.9 | 18.7 |
| WebDev Arena | 1,674 · max | 1,672 · max |
| SciCode | 52.1 | 53.2 |
| DeepSWE 1.1 | — | 57.5 · xhigh |
| FrontierCode 1.1 | 43.2 | — |
| Terminal-Bench Science 0.1 | 11.9 | — |
Specs
| Spec | Qwen Max (0902) | Qwen Max |
|---|---|---|
| Input, per 1M | !$2 | $2 |
| Output, per 1M | !$6 | $6 |
| Cost per task? | $5.41 | $2.67 |
| Speed, tok/s | 40 | 38 |
| Context | 984K | 1M |
| Weights | Closed | Closed |
| Released | Sep 2026 | Aug 2026 |
| See images | ✓ | ✓ |
| Read PDFs | ? | Partial |
| Hear audio | — | — |
| Watch video | ✓ | ✓ |
| Call tools | ✓ | ✓ |
| Force a tool call | ? | Partial |
| Return strict JSON | ✓ | ✓ |
| Search the web | ? | ? |
| Run code | ? | ? |
| Use a computer | ? | ? |
What breaks when you switch
Qwen Max (0902) → Qwen Max
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.
File is not delivered · QwenCloud / Responses›
PDF input through Responses returns HTTP 200 without delivering the file to the model; use Chat Completions or DashScope.
Not simultaneously · QwenCloud›
Setting reasoning_effort and thinking_budget together returns an error; set only one.
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 Max → Qwen Max (0902)