New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
Qwen3-235B-A22B
About Qwen3-235B-A22B
Qwen3-235B-A22B is an AI model developed by Qwen, in the language category, released in 2025, made available as an open-weights model with 235B params.
On this page you'll find Qwen3-235B-A22B's full specifications, including 53 benchmark results. Review provider pricing and benchmark scores below, or compare Qwen3-235B-A22B head-to-head with other language models.
Links
Run Qwen3-235B-A22B locally — what to buy
Share this build ↗Sized to what Qwen3-235B-A22B actually needs (~8k context at Q4), not to the biggest GPU: Good = cheapest that runs it, Better = best value, Best = most headroom. Speed is a hardware estimate; anything past ~120 tok/s is shown as instant.
Software support
✓ measured · · compatible · — not supported. Informational only — speed is hardware-based.
Community
No reports yet. Own this model on some hardware? Be the first to confirm it runs.
No comments yet. Start the discussion.
Qwen3-235B-A22B benchmark scores▶
| Benchmark | Category | Score | Variant |
|---|---|---|---|
| Codeforces Elo | code | 2,056 | thinking-rating |
| Codeforces Elo | code | 1,387 | non-thinking-rating |
| LiveCodeBench v5 | code | 70.7% | thinking-pass@1 |
| LiveCodeBench v5 | code | 56.64% | |
| LiveCodeBench v5 | code | 35.3% | non-thinking-pass@1 |
| AlignBench v1.1 | general | 8.94 | thinking-v1-1 |
| AlignBench v1.1 | general | 8.91 | non-thinking-v1-1 |
| ArenaHard | general | 96.1% | non-thinking |
| ArenaHard | general | 95.6% | thinking |
| C-Eval | general | 89.6% | thinking |
| C-Eval | general | 86.1% | non-thinking |
| Creative Writing v3 | general | 84.6 | thinking |
| Creative Writing v3 | general | 80.4 | non-thinking |
| IFEval | general | 83.4% | thinking-strict-prompt |
| IFEval | general | 83.2% | non-thinking-strict-prompt |
| LiveBench | general | 77.1 | thinking-2024-11-25 |
| LiveBench | general | 62.5 | non-thinking-2024-11-25 |
| MMLU-Redux | general | 92.7% | thinking |
| MMLU-Redux | general | 89.2% | non-thinking |
| MMMLU | general | 84.3% | thinking-14lang |
| MMMLU | general | 79.8% | non-thinking-14lang |
| Multi-IF | general | 71.9 | thinking |
| Multi-IF | general | 70.2 | non-thinking |
| WritingBench | general | 8.03 | thinking |
| WritingBench | general | 7.7 | non-thinking |
| INCLUDE | knowledge | 78.7 | thinking |
| INCLUDE | knowledge | 75.6 | non-thinking |
| AIME 2024 | math | 86.68% | |
| AIME 2024 | math | 85.7% | thinking |
| AIME 2024 | math | 40.1% | non-thinking |
| AIME 2025 | math | 81.5% | thinking |
| AIME 2025 | math | 75.43% | |
| AIME 2025 | math | 24.7% | non-thinking |
| HMMT February 2025 | math | 61.88% | |
| MATH-500 | math | 98% | thinking |
| MATH-500 | math | 91.2% | non-thinking |
| MT-AIME 2024 | math | 80.8 | thinking-mt-2024 |
| MT-AIME 2024 | math | 32.4 | non-thinking-mt-2024 |
| Omni-MATH-HARD | math | 56.91% | |
| PolyMath-en | math | 54.7 | thinking |
| PolyMath-en | math | 27 | non-thinking |
| AutoLogi | reasoning | 89 | thinking |
| AutoLogi | reasoning | 83.3 | non-thinking |
| GPQA Diamond | reasoning | 71.1% | thinking |
| GPQA Diamond | reasoning | 65.55% | |
| GPQA Diamond | reasoning | 62.9% | non-thinking |
| Humanity's Last Exam | reasoning | 14.23% | |
| MLogiQA | reasoning | 77.1 | thinking |
| MLogiQA | reasoning | 67.6 | non-thinking |
| ZebraLogic | reasoning | 80.3% | thinking |
| ZebraLogic | reasoning | 37.7% | non-thinking |
| BFCL v3 | tool-use | 70.8% | thinking |
| BFCL v3 | tool-use | 68% | non-thinking |
More models like Qwen3-235B-A22B
Frequently asked questions
What is Qwen3-235B-A22B? ▶
Qwen3-235B-A22B is an AI model developed by Qwen, in the language category, released in 2025. It is tracked on GenAIList with its specifications, benchmark scores and provider pricing.
Who created Qwen3-235B-A22B? ▶
Qwen3-235B-A22B was developed by Qwen and released in 2025.
Is Qwen3-235B-A22B open source or proprietary? ▶
Qwen3-235B-A22B ships as an open-weights model: you can download and self-host the weights, though the licence may place some restrictions on use.
How much does Qwen3-235B-A22B cost? ▶
Pricing for Qwen3-235B-A22B depends on the provider. See the providers table on this page for the latest API rates.
How does Qwen3-235B-A22B perform on benchmarks? ▶
Qwen3-235B-A22B is benchmarked across 53 evaluations on GenAIList, including Codeforces Elo (2,056). See the full benchmark table below and compare it with other models.
No videos yet. Know a good one? Add it below.
Know a great video about Qwen3-235B-A22B?
Add YouTube Video
Add Tweet/Discussion
Report an Issue
Help us maintain accurate information in our database.
Suggest an Edit
Tell us what needs to be changed or corrected for