Qwen3-8B places in the top three on AutoLogi.
Qwen Released 28 Apr 2025 Qwen Apr 2025 Open weights
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 | |
|---|---|---|---|---|
| Vectara Hallucination Leaderboard (2025 dataset) | 4.80% | #9 of 104 | Official leaderboard | |
| AlGhafa | 74.8% | #7 of 39 | Official leaderboard | |
| ArbMMLU-HT | 61.5% | #7 of 39 | Official leaderboard | |
| ArabicMMLU | 65% | #8 of 39 | Official leaderboard | |
| Open Arabic LLM Leaderboard v2 | 66.2% | #8 of 39 | Official leaderboard | |
| ALRAGE | 78.2% | #12 of 39 | Official leaderboard | |
| MadinahQA | 52.2% | #14 of 39 | Official leaderboard | |
| AlignBench | 8.46 | #6 of 15 | Model card | |
| Arena-Hard-Auto | 85.8% | #16 of 39 | Model card | |
| Fiction.LiveBench | 62.1% | #31 of 57 | Epoch AI | |
| RULER | 89.1% | #21 of 38 | Model card | |
| Multi-IF | 71.2% | #16 of 28 | Model card | |
| IFEval | 85% | #74 of 126 | Model card | |
| Phare | 63.9% | #38 of 62 | Official leaderboard | |
| MLogiQA | 69% | #5 of 8 | Model card | |
| MathIF | 37.9% | #8 of 12 | Official leaderboard | |
| MMLU-Redux | 87.5% | #26 of 38 | Model card | |
| MT-AIME2024 | 65.4% | #5 of 7 | Model card | |
| Vectara Hallucination Leaderboard (HHEM) | 3.00% | #106 of 148 | Official leaderboard | |
| INCLUDE | 67.8% | #18 of 25 | Model card | |
| C-Eval | 83.4% | #29 of 38 | Model card | |
| WritingBench | 7.59 | #11 of 14 | Model card | |
| MMMLU | 74.4% | #49 of 62 | Model card | |
| SEA-HELM | 60.3 | #50 of 62 | Official leaderboard | |
| Creative Writing v3 | 75.0 | #10 of 12 | Model card | |
| EQ-Bench 3 | 909 | #67 of 78 | Official leaderboard |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MATH-500 | 97.4% | #13 of 67 | Model card | |
| AutoLogi | 89.1% | #3 of 8 | Model card | |
| ZebraLogic | 84.8% | #13 of 23 | Model card | |
| AIME 2024 | 76% | #50 of 87 | Model card | |
| OTIS Mock AIME 2024-2025 | 56.1% | #119 of 202 | Epoch AI | |
| GPQA Diamond | 56.8% | #131 of 219 | Epoch AI | |
| HiPhO | 31.4% | #27 of 35 | Official leaderboard | |
| DTBench | 32.9% | #144 of 178 | Official leaderboard | |
| AIME 2025 | 67.3% | #116 of 143 | Model card | |
| PolyMath | 42.7% | #15 of 18 | Model card | |
| CritPt | 0% | #134 of 160 | Epoch AI |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Codeforces rating | 1,785 | #29 of 41 | Model card | |
| LiveCodeBench v5 | 57.5% | #32 of 44 | Model card | |
| AutoCodeBench | 28.5% | #29 of 34 | Official leaderboard |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| BFCL V4 | 42.6% | #25 of 65 | Official leaderboard | |
| SnakeBench | 25 | #75 of 183 | Official leaderboard | |
| Berkeley Function Calling Leaderboard (BFCL) | 68.1% | #28 of 47 | Model card | |
| LisanBench | 51.3 | #123 of 133 | Official leaderboard |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| AraTrust | 83.4% | #10 of 39 | Official leaderboard |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| LiveBench | 67.1% | #14 of 27 | Model card | |
| ACCoRD | 41.8 | #128 of 150 | Official leaderboard | |
| Conceptual Reasoning Index | 20.2 | #133 of 149 | Official leaderboard | |
| LMCA | 8.82% | #130 of 139 | Epoch AI |
Qwen's models in color, against every other model on the Epoch Capabilities Index, by release date.
Every result in the longer documents the lab published with it. 24 of them aren't in the launch post.