Alibaba (Qwen)
Qwen3-235B-A22B-Thinking (Jul 2025) benchmark results
4 results on 4 benchmarks from 3 sources.
Open weights Released: Jul 25, 2025 Updated Oct 22, 2026
Also listed as: qwen3-235b-a22b-thinking-2507 · Qwen3-235B-A22B-Thinking-2507
All benchmark results
| Benchmarks | Score | Rank | Setting | Source type | Date |
|---|---|---|---|---|---|
| LMArena Text | 1400 | 161 | Overall, style control on; 8822 votes; 95% CI 1393–1407“qwen3-235b-a22b-thinking-2507” | Official leaderboard | Oct 8, 2026 |
| GPQA Diamond | 80.0% | 115 | Epoch AI run, accuracy | Independent run | Dec 11, 2025 |
| MMLU-Pro | 84.5% | 38 | Overall accuracy; data source: Self-Reported; 235B“Qwen3-235B-A22B-Thinking-2507” | Vendor-reported | Mar 11, 2026 |
| AIME (OTIS Mock AIME 2024–2025) | 86.7% | 84 | Epoch AI run, OTIS Mock AIME 2024–2025 | Independent run | Dec 10, 2025 |
FAQ
Where do these Qwen3-235B-A22B-Thinking (Jul 2025) scores come from?
From Epoch AI Benchmarking Hub, LMArena leaderboard dataset, and MMLU-Pro leaderboard (TIGER-Lab). Each row links to the original leaderboard, dataset or report, and vendor-reported numbers are labelled.