New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
Qwen3-235B-A22B-Thinking (Jul 2025)
About Qwen3-235B-A22B-Thinking (Jul 2025)
Qwen3-235B-A22B-Thinking (Jul 2025) 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-Thinking (Jul 2025)'s full specifications, including 41 benchmark results. Review provider pricing and benchmark scores below, or compare Qwen3-235B-A22B-Thinking (Jul 2025) head-to-head with other language models.
Links
Run Qwen3-235B-A22B-Thinking (Jul 2025) locally — what to buy
Share this build ↗Sized to what Qwen3-235B-A22B-Thinking (Jul 2025) 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-Thinking (Jul 2025) benchmark scores▶
| Benchmark | Category | Score | Variant |
|---|---|---|---|
| Codeforces Elo | code | 2,055 | thinking-rating-cited-ring-1t |
| LiveCodeBench | code | 78.2% | 2407-2501 |
| LiveCodeBench v5 | code | 70.7% | reasoning |
| LiveCodeBench v6 | code | 75.72% | thinking-cited-ring-1t |
| LiveCodeBench v6 | code | 58.9% | reasoning |
| SciCode | code | 42.9% | |
| Aider Benchmark | coding | 88.91 | thinking-cited-ring-1t |
| ArenaHard v2 | general | 80.18 | thinking-win-rate-cited-ring-1t |
| C-Eval | general | 93.13% | thinking-cited-ring-1t |
| IFEval | general | 87.8% | thinking-cited-ring-1t |
| IFEval | general | 83.4% | reasoning |
| MMLU-Pro | general | 84.5% | |
| MMLU-Pro | general | 84.4% | thinking-cited-ring-1t |
| MMLU-Pro | general | 83% | reasoning |
| MMLU-Redux | general | 92.7% | reasoning |
| MultiChallenge | general | 52.75% | thinking-cited-ring-1t |
| AGIEval | knowledge | 90.01 | thinking-cited-ring-1t |
| CMMLU | knowledge | 90.64 | thinking-cited-ring-1t |
| TriviaQA | knowledge | 79.63 | thinking-cited-ring-1t |
| AIME 2024 | math | 94.1% | |
| AIME 2025 | math | 92.3% | thinking-cited-ring-1t |
| AIME 2025 | math | 81.5% | reasoning |
| CNMO 2024 | math | 89.5% | thinking-cited-ring-1t |
| HMMT February 2025 | math | 83.9% | thinking-cited-ring-1t |
| HMMT February 2025 | math | 62.5% | reasoning |
| MATH-500 | math | 98% | |
| Omni-MATH | math | 82.52 | thinking-cited-ring-1t |
| UGMathBench | math | 77 | thinking-cited-ring-1t |
| ARC-AGI-1 | reasoning | 48.12 | thinking-cited-ring-1t |
| BBEH | reasoning | 60 | thinking-cited-ring-1t |
| FinanceReasoning | reasoning | 87.65 | thinking-cited-ring-1t |
| GPQA Diamond | reasoning | 81.1% | |
| GPQA Diamond | reasoning | 81.1% | thinking-cited-ring-1t |
| GPQA Diamond | reasoning | 71.1% | reasoning |
| Humanity's Last Exam | reasoning | 15.8% | |
| Humanity's Last Exam | reasoning | 13.95% | thinking-cited-ring-1t |
| ZebraLogic | reasoning | 97.03% | thinking-cited-ring-1t |
| HealthBench | safety | 55.56% | thinking-cited-ring-1t |
| PhyBench | science | 42.61 | thinking-cited-ring-1t |
| BFCL v3 | tool-use | 73.53% | thinking-cited-ring-1t |
| BFCL v3 | tool-use | 70.8% | reasoning |
More models like Qwen3-235B-A22B-Thinking (Jul 2025)
Frequently asked questions
What is Qwen3-235B-A22B-Thinking (Jul 2025)? ▶
Qwen3-235B-A22B-Thinking (Jul 2025) 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-Thinking (Jul 2025)? ▶
Qwen3-235B-A22B-Thinking (Jul 2025) was developed by Qwen and released in 2025.
Is Qwen3-235B-A22B-Thinking (Jul 2025) open source or proprietary? ▶
Qwen3-235B-A22B-Thinking (Jul 2025) 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-Thinking (Jul 2025) cost? ▶
Pricing for Qwen3-235B-A22B-Thinking (Jul 2025) depends on the provider. See the providers table on this page for the latest API rates.
How does Qwen3-235B-A22B-Thinking (Jul 2025) perform on benchmarks? ▶
Qwen3-235B-A22B-Thinking (Jul 2025) is benchmarked across 41 evaluations on GenAIList, including Codeforces Elo (2,055). 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-Thinking (Jul 2025)?
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