Qwen3.6-27B: benchmarks, price and rank
Qwen3.6-27B from Alibaba is 87th of 123 rated AI models on Spezia's leaderboard. It costs $0.32 in, $3.20 out per million tokens.
- 87th of 123 rated models
- Rating 920
- Rated on 9 benchmarks
- Open weights
- Released Apr 21, 2026
- 262,000 tokens of context
Where it is strongest
Not in the top tenth on any benchmark in use.
Where it falls behind
- 15th of 18 on IMO-AnswerBench
- 62nd of 76 on FrontierMath
- 39th of 50 on SWE-Bench Pro
Price: $0.32 in, $3.20 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.
- SWE-Bench Pro53.5%
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.
39th of 50. The maker's own number, from Alibaba Cloud / Qwen Team, via LLM Stats.
- Humanity's Last Exam24%
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.
48th of 74. The maker's own number, from Alibaba Cloud / Qwen Team, via LLM Stats.
- LiveCodeBench v683.9%
Programming contest problems collected after models were trained, from LeetCode, AtCoder and Codeforces.
14th of 43. The maker's own number, from Alibaba Cloud / Qwen Team, via LLM Stats.
- FrontierMath35.1%
Hundreds of new, unpublished math problems written by mathematicians, from hard undergraduate level up to research, with answers a computer can check.
62nd of 76. Independent result from Epoch AI.
- MMMU-Pro75.8%
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.
29th of 51. The maker's own number, from Alibaba Cloud / Qwen Team, via LLM Stats.
- CharXiv Reasoning78.4%
Questions about real charts from scientific papers that need reasoning across the chart, not just reading off a value.
30th of 45. The maker's own number, from Alibaba Cloud / Qwen Team, via LLM Stats.
- IMO-AnswerBench80.8%
Problems from the International Mathematical Olympiad, the hardest contest for school students, where the model has to reach the right final answer.
15th of 18. The maker's own number, from Alibaba Cloud / Qwen Team, via LLM Stats.
- ERQA62.5%
400 questions about images of the physical world: space, motion, actions, the state of objects and views from several cameras.
12th of 21. The maker's own number, from Alibaba Cloud / Qwen Team, via LLM Stats.
- SWE-bench Verified77.2%
Real bug reports and feature requests from popular open-source Python projects. The model has to change the code so the project's hidden tests pass.
12th of 56. The maker's own number, from Alibaba Cloud / Qwen Team, via LLM Stats.
- GPQA Diamond85.9%
Graduate-level questions in biology, physics and chemistry, written by PhDs so that searching the web does not give the answer away.
71st of 103. Independent result from Epoch AI.
3 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.