Qwen3.8 Max: benchmarks, price and rank
Qwen3.8 Max from Alibaba is 22nd of 123 rated AI models on Spezia's leaderboard, strongest on OSWorld-Verified and ERQA. It costs $1.65 in, $4.95 out per million tokens.
- 22nd of 123 rated models
- Rating 1,571
- First on 1 of 16 benchmarks
- Closed
- Released Aug 2, 2026
- 1 million tokens of context
Where it is strongest
- 1st of 25 on OSWorld-Verified
- 1st of 21 on ERQA
- 6th of 51 on MMMU-Pro
- 3rd of 24 on MRCR v2 (8 needles)
Where it falls behind
- 26th of 27 on DeepSWE 1.1
- 20th of 21 on FrontierSWE
Price: $1.65 in, $4.95 out per million tokens.
Its headline results
The benchmarks that count most in the rating, with its place among the models measured the same way, and where each number came from.
- APEX-Agents63.3%
Long tasks written by investment banking analysts, management consultants and corporate lawyers from their own work, done across files and apps in a realistic work setup.
18th of 56. Independent result from Epoch AI.
- SWE-Bench Pro67.7%
Long changes to real codebases in several languages, often across many files, including code from private and copyleft projects that models are unlikely to have seen.
6th of 50. The maker's own number, from Alibaba Cloud / Qwen Team, via LLM Stats.
- FrontierSWE17.8%
Open-ended technical projects that take hours to tens of hours, from making systems faster to building large programs and applied machine learning research. Each run gets a 20-hour budget.
20th of 21. Independent result from Epoch AI.
- Humanity's Last Exam43.6%
About 2,500 questions written by experts in more than a hundred fields to be as hard as they could make them, many needing a diagram or image.
24th of 74. The maker's own number, from Alibaba Cloud / Qwen Team, via LLM Stats.
- OSWorld-Verified86.1%
Ordinary tasks on a real desktop computer using normal apps: a browser, a spreadsheet, an email client, a photo editor, the file manager.
1st of 25. The maker's own number, from Alibaba Cloud / Qwen Team, via LLM Stats.
- Toolathlon72.5%
Long tasks across many real apps and their tools, such as email, calendars, spreadsheets, code repositories and online stores.
8th of 37. The maker's own number, from Alibaba Cloud / Qwen Team, via LLM Stats.
- DeepSWE 1.156.6%
Software engineering tasks run in the same simple agent setup for every model.
26th of 27. The maker's own number, from Alibaba Cloud / Qwen Team, via LLM Stats.
- SimpleQA Verified47.3%
Short factual questions with one checked answer, asked without web search.
36th of 78. Independent result from Epoch AI.
- FrontierMath74.7%
Hundreds of new, unpublished math problems written by mathematicians, from hard undergraduate level up to research, with answers a computer can check.
25th of 76. Independent result from Epoch AI.
- MMMU-Pro82.3%
College exam questions that need a picture to answer, such as charts, diagrams, maps and chemical structures, with more answer options than the original MMMU and some questions shown only as a screenshot.
6th of 51. The maker's own number, from Alibaba Cloud / Qwen Team, via LLM Stats.
9 more results in its full profile.
Every result with its source, what it costs per task, what jumped with its release, side by side with any other model, and answers to your questions about when to use it.
Models ranked near it
How the rating works, and every benchmark it uses: the model leaderboard.