Qwen3-235B-A22B-Thinking-2507
Zero-eval
#1MMLU-Redux
#1AIME25
#1WritingBench
+14 more
by Alibaba Cloud / Qwen Team
About
Qwen3-235B-A22B-Thinking-2507 is a language model developed by Alibaba Cloud / Qwen Team. It achieves strong performance with an average score of 69.2% across 25 benchmarks. It excels particularly in MMLU-Redux (93.8%), AIME25 (92.3%), WritingBench (88.3%). It supports a 387K token context window for handling large documents. The model is available through 1 API provider. It's licensed for commercial use, making it suitable for enterprise applications. Released in 2025, it represents Alibaba Cloud / Qwen Team's latest advancement in AI technology.
Pricing Range
Input (per 1M)$0.30 -$0.30
Output (per 1M)$3.00 -$3.00
Providers1
Timeline
AnnouncedJul 25, 2025
ReleasedJul 25, 2025
Specifications
License & Family
License
Apache 2.0
Base ModelQwen3 235B A22B
Benchmark Performance Overview
Performance metrics and category breakdown
Overall Performance
25 benchmarks
Average Score
69.2%
Best Score
93.8%
High Performers (80%+)
11Performance Metrics
Max Context Window
387.1KTop Categories
factuality
93.8%
roleplay
78.4%
general
77.4%
reasoning
64.9%
math
60.1%
Additional Information
Content coming soon...
All Benchmark Results for Qwen3-235B-A22B-Thinking-2507
Complete list of benchmark scores with detailed information
| MMLU-Redux | factuality | text | 0.94 | 93.8% | Self-reported |
| AIME25 | general | text | 0.92 | 92.3% | Self-reported |
| WritingBench | general | text | 0.88 | 88.3% | Self-reported |
| IFEval | code | text | 0.88 | 87.8% | Self-reported |
| Creative Writing v3 | general | text | 0.86 | 86.1% | Self-reported |
| MMLU-Pro | general | text | 0.84 | 84.4% | Self-reported |
| HMMT25 | general | text | 0.84 | 83.9% | Self-reported |
| GPQA | general | text | 0.81 | 81.1% | Self-reported |
| MMLU-ProX | general | text | 0.81 | 81.0% | Self-reported |
| Include | general | text | 0.81 | 81.0% | Self-reported |
Showing 1 to 10 of 25 benchmarks