Qwen3-1.7B.
Qwen Released 29 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 | |
|---|---|---|---|---|
| ArabicMMLU | 49.7% | #17 of 39 | Official leaderboard | |
| ArbMMLU-HT | 43.9% | #19 of 39 | Official leaderboard | |
| Vectara Hallucination Leaderboard (HHEM) | 4.40% | #75 of 148 | Official leaderboard | |
| Open Arabic LLM Leaderboard v2 | 52.9% | #20 of 39 | Official leaderboard | |
| AlGhafa | 56.8% | #21 of 39 | Official leaderboard | |
| MadinahQA | 40% | #23 of 39 | Official leaderboard | |
| ALRAGE | 66.3% | #24 of 39 | Official leaderboard | |
| MathIF | 30.2% | #9 of 12 | Official leaderboard | |
| AlignBench | 7.60 | #13 of 15 | Model card | |
| MLogiQA | 56% | #7 of 8 | Model card | |
| MMMLU | 59.1% | #55 of 62 | Model card | |
| IFEval | 72.5% | #114 of 126 | Model card | |
| Wer wird Millionär? LLM Benchmark | 84.0 | #70 of 76 | Official leaderboard | |
| C-Eval | 68.1% | #35 of 38 | Model card | |
| Arena-Hard-Auto | 43.1% | #36 of 39 | Model card | |
| Multi-IF | 51.2% | #26 of 28 | Model card | |
| INCLUDE | 51.8% | #24 of 25 | Model card | |
| MMLU-Redux | 73.9% | #37 of 38 | Model card | |
| WritingBench | 7.02 | #14 of 14 | Model card | |
| Creative Writing v3 | 48.0 | #12 of 12 | Model card | |
| MT-AIME2024 | 36.1% | #7 of 7 | Model card |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MATH-500 | 93.4% | #47 of 67 | Model card | |
| OTIS Mock AIME 2024-2025 | 8.06% | #156 of 202 | Epoch AI | |
| GPQA Diamond | 38% | #180 of 219 | Epoch AI | |
| AIME 2024 | 48.3% | #75 of 87 | Model card | |
| ZebraLogic | 63.2% | #21 of 23 | Model card | |
| AIME 2025 | 36.8% | #135 of 143 | Model card | |
| PolyMath | 25.2% | #18 of 18 | Model card | |
| AutoLogi | 83.2% | #8 of 8 | Model card |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| LiveCodeBench v5 | 33.2% | #39 of 44 | Model card | |
| AutoCodeBench | 11.2% | #33 of 34 | Official leaderboard |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| BFCL V4 | 28.4% | #42 of 65 | Official leaderboard | |
| LisanBench | 133.3 | #105 of 133 | Official leaderboard | |
| Berkeley Function Calling Leaderboard (BFCL) | 56.6% | #44 of 47 | Model card |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| AraTrust | 75.6% | #20 of 39 | Official leaderboard |
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| LiveBench | 51.1% | #19 of 27 | Model card |
Every result in the longer documents the lab published with it. 23 of them aren't in the launch post.