Qwen3-235B-A22B-Thinking ranks first on StockBench.
Qwen Jul 2025 Jul 2025 snapshot Open weights Flagship
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| WritingBench | 82.3 | #2 of 45 | Official leaderboard | |
| LongBench v2 | 60.6% | #3 of 33 | Official leaderboard | |
| Multi-IF | 80.6% | #4 of 28 | Model card | |
| Arena-Hard v2.0 | 79.7% | #5 of 24 | Model card | |
| MMLU-Redux | 93.8% | #8 of 38 | Model card | |
| MMLU-Pro | 84.4% | #36 of 151 | Model card | |
| SimpleQA Verified | 53.7% | #14 of 56 | Official leaderboard | |
| Lech Mazur Creative Writing | 8.24 | #11 of 44 | Epoch AI | |
| Fiction.LiveBench | 75% | #15 of 57 | Epoch AI | |
| LMArena (Elo) | 1,400 | #130 of 333 | Official leaderboard | |
| IFEval | 87.8% | #50 of 126 | Model card | |
| INCLUDE | 81% | #10 of 25 | Model card | |
| MMLU-ProX | 81% | #7 of 17 | Model card | |
| SuperGPQA | 64.9% | #12 of 26 | Model card | |
| LLM Confabulation Leaderboard | 16.8% | #29 of 58 | Official leaderboard | |
| MultiNRC | 27.1% | #22 of 38 | Official leaderboard | |
| Creative Writing v3 | 63.8 | #74 of 120 | Official leaderboard | |
| Humanity's Last Exam | 18.2% | #106 of 147 | Model card |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| AMO-Bench | 47.8% | #2 of 21 | Official leaderboard | |
| PHYBench | 35% | #6 of 28 | Official leaderboard | |
| AIME 2025 | 92.3% | #39 of 143 | Model card | |
| HiPhO | 61.5% | #10 of 35 | Official leaderboard | |
| OTIS Mock AIME 2024-2025 | 86.7% | #69 of 202 | Epoch AI | |
| GPQA Diamond | 80% | #87 of 219 | Epoch AI | |
| ForecastBench | 62.1 | #38 of 86 | Official leaderboard | |
| PolyMath | 60.1% | #8 of 18 | Model card | |
| DTBench | 67.1% | #88 of 178 | Official leaderboard | |
| MathArena (Apex, IMO, USAMO) | 5.21% | #25 of 47 | Official leaderboard | |
| FrontierMath | 8.48% | #39 of 70 | Epoch AI | |
| HMMT 2025 | 83.9% | #31 of 49 | Model card | |
| CritPt | 0% | #137 of 160 | Epoch AI | |
| General365 | 47.9% | #20 of 23 | Official leaderboard | |
| FrontierMath Tier 4 | 0% | #51 of 55 | Epoch AI |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| ArtifactsBench | 55% | #6 of 20 | Official leaderboard | |
| AutoCodeBench | 47.7% | #11 of 34 | Official leaderboard | |
| Codeforces rating | 2,134 | #15 of 41 | Model card | |
| LiveCodeBench v6 | 74.1% | #43 of 76 | Model card | |
| WeirdML | 41% | #73 of 112 | Official leaderboard | |
| OJBench | 32.5% | #8 of 12 | Model card |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Berkeley Function Calling Leaderboard (BFCL) | 71.9% | #16 of 47 | Model card | |
| LisanBench | 803.7 | #60 of 133 | Official leaderboard | |
| Meta Agents Research Environments (ARE) / Gaia2 | 15.7% | #8 of 13 | Official leaderboard | |
| Pencil Puzzle Bench | 0% | #35 of 53 | Official leaderboard | |
| Galileo Agent Leaderboard v2 | 34% | #15 of 21 | Official leaderboard | |
| VITA-Bench | 14.5% | #13 of 18 | Official leaderboard | |
| tau-bench | 56.9% | #18 of 23 | Model card | |
| Mystery Game Puzzles | 9.00% | #67 of 80 | Epoch AI | |
| SnakeBench | 17 | #157 of 183 | Official leaderboard | |
| tau2-bench | 58.5% | #61 of 69 | Model card |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| StockBench | 2.50% | #1 of 13 | Official leaderboard | |
| ProfBench | 41.1% | #62 of 72 | Official leaderboard | |
| Vending-Bench 2 | $-11 | #63 of 66 | Official leaderboard |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Agentic BAIM-LLM Evaluation (ABLE) | 45.2% | #11 of 16 | Official leaderboard | |
| Human Pathogen Capabilities Test v2 (HPCT v2) | 43.1% | #54 of 71 | Official leaderboard |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| LiveBench | 78.4% | #3 of 27 | Model card | |
| Conceptual Reasoning Index | 42.4 | #90 of 149 | Official leaderboard | |
| LMCA | 29.3% | #84 of 139 | Epoch AI | |
| ACCoRD | 57.1 | #96 of 150 | Official leaderboard |
Qwen's models in color, against every other model on the Epoch Capabilities Index, by release date.
The benchmarks the lab chose to headline, with the scores it gave.