Qwen3.8 Max (0902) vs Qwen3.8 Max
| Benchmark | Qwen Max (0902) | Qwen Max |
|---|---|---|
| Humanity's Last Exam | 43.1 | 43 |
| AA Omniscience Index | 12 | 3.4 |
| CritPt (physics) | 17.7 | 20 |
| AA Intelligence Index 4.3.2 | 45.4 | 40.2 |
| AA Omniscience · Accuracy | 31.7 | 31.9 |
| AA Omniscience · Hallucination Rate | 28.8 | 41.7 |
| AA-LCR (long context) 1.1 | 80.3 | 78.3 |
| GDP.pdf · AA all-pass | 22.8 | 20.2 |
| MLCR-AA | 20 | 26.1 |
| Vals Legal Research Bench | 46.2 | 47.6 · max |
| Arena Text · overall | — | 1,482 · max |
| Arena Text · Chinese | — | 1,538.8 · max |
| Arena Text · English | — | 1,492.1 · max |
| Arena Text · French | — | 1,502.1 · max |
| Arena Text · German | — | 1,475.7 · max |
| Arena Text · instruction following | — | 1,480.7 · max |
| Arena Text · Japanese | — | 1,472.6 · max |
| Arena Text · Korean | — | 1,461.8 · max |
| Arena Text · non-English | — | 1,472.6 · max |
| Arena Text · Polish | — | 1,471 · max |
| Arena Text · Russian | — | 1,481.7 · max |
| Arena Text · Spanish | — | 1,487.4 · max |
| SimpleQA Verified v1 | 47.3 · xhigh | — |
| Chess Puzzles | 37 · xhigh | — |
| FrontierMath Tier 4 (v2) | 34.1 · xhigh | — |
| FrontierMath Tiers 1–3 (v2) | 65.6 · xhigh | — |
| MathArena · ArXivMath · April 2026 | — | 59.2 · max |
| MathArena · ArXivMath · August 2026 | — | 57.9 · max |
| MathArena · ArXivMath · June 2026 | — | 75.7 · max |
| MathArena · ArXivMath · May 2026 | — | 69.2 · max |
| MathArena · BrokenArXiv · April 2026 | — | 45.5 · max |
| MathArena · BrokenArXiv · August 2026 | — | 69.6 · max |
| MathArena · BrokenArXiv · June 2026 | — | 44 · max |
| MathArena · BrokenArXiv · May 2026 | — | 32.5 · max |
| MathArena · ArXivLean · June 2026 | — | 45.7 · max |
| Vals LegalBench | — | 83.6 · max |
| Vals MedCode | — | 40.7 · max |
| Vals MedScribe | — | 85 · max |
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 | 41 | 41 |
| 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)