Qwen3 32B
Qwen / Qwen
52scores
42benchmarks
$0.08 / $0.24 per 1M tokenscost in/out
Metadata
Qwen Open source
Aliases: qwen-qwen3-32b, qwen-qwen3-32b-04-28, qwen/qwen3-32b, qwen/qwen3-32b-04-28, qwen3-32b, qwen3-32b-04-28
| Benchmark | Category | Rank | Score | Sampled |
|---|---|---|---|---|
| ADBench | Agentic | 9 | 59 | 2026-05-06 |
| AgentIF | Agentic | 3 | 58.4 | 2026-05-27 |
| AMA-Bench | Agentic | 6 | 0.51 | 2026-05-06 |
| Berkeley Function-Calling Leaderboard | Agentic | 29 | 48.71% | 2026-05-27 |
| Berkeley Function-Calling Leaderboard | Agentic | 33 | 46.78% | 2026-05-27 |
| CAR-bench | Agentic | 10 | 0.31 | 2026-05-06 |
| Tau2-Bench Telecom | Agentic | 243 | 29.8% | 2026-05-11 |
| Terminal-Bench Hard | Agentic | 304 | 3% | 2026-05-11 |
| VitaBench | Agentic | 14 | 5.30 | 2026-05-06 |
| VitaBench | Agentic | 25 | 4 | 2026-05-06 |
| WildAgtEval | Agentic | 8 | 49.9% | 2026-05-28 |
| OpenUGI | Alignment | 778 | 31.02 | 2026-05-06 |
| OpenUGI | Alignment | 981 | 25.03 | 2026-05-06 |
| Stick To Your Role! | Alignment | 9 | 0.74 | 2026-05-06 |
| ABC-Bench | Coding | 10 | 8.9% +/- 1.1 | 2026-05-27 |
| Codeforces | Coding | 13 | 0.659 | 2026-05-28 |
| SciCode | Coding | 190 | 35.4% | 2026-05-11 |
| SciCode | Coding | 282 | 28% | 2026-05-11 |
| NeoEvalPlusN | Creative | 143 | 9.50 | 2026-05-06 |
| RedSage-Bench | Cybersecurity | 3 | 85.4% | 2026-05-28 |
| MMTU | Data | 14 | 0.51 | 2026-05-06 |
| MMTU | Data | 23 | 0.38 | 2026-05-06 |
| GSMA Open Telco Leaderboard | Domain | 51 | 46.77 | 2026-05-06 |
| EduGuardBench | Education | 6 | 0.72 | 2026-05-27 |
| Vectara HHEM Hallucination Leaderboard | Factuality | 24 | 94.10 | 2026-05-06 |
| BizFinBench | Finance | 8 | 68.26 | 2026-05-27 |
| Arena-Hard | Generalization | 16 | 44.5% | 2026-05-27 |
| GeoCode Leaderboard | Geospatial | 12 | 60.67% pass@1 | 2026-05-28 |
| HealthBench Hard | Healthcare | 9 | 0.5 | 2026-05-27 |
| Artificial Analysis Intelligence Index | Intelligence | 292 | 16.53 | 2026-05-11 |
| Artificial Analysis Intelligence Index | Intelligence | 334 | 14.53 | 2026-05-11 |
| FACTS Grounding | Intelligence | 7 | 0.42 | 2026-05-06 |
| Humanity's Last Exam | Intelligence | 182 | 8.3% | 2026-05-11 |
| Humanity's Last Exam | Intelligence | 386 | 4.3% | 2026-05-11 |
| MMLU-Pro | Intelligence | 120 | 79.8% | 2026-05-11 |
| MMLU-Pro | Intelligence | 200 | 72.7% | 2026-05-11 |
| TableBench | Intelligence | 13 | 52.45% | 2026-05-27 |
| AraGen v3 | Language | 34 | 35.18 | 2026-05-06 |
| Open Arabic LLM Leaderboard | Language | 131 | 41.17 | 2026-05-06 |
| Open Portuguese LLM Leaderboard | Language | 55 | 85.43 | 2026-05-06 |
| J1-ENVS | Legal | 3 | 59.14 | 2026-05-26 |
| LEXam | Legal | 26 | 40.00% open / 45.30% MCQ | 2026-05-28 |
| ConStory-Bench | Long Context | 6 | CED 0.537 | 2026-05-28 |
| AIME 2025 | Math | 88 | 73% | 2026-05-11 |
| AIME 2025 | Math | 210 | 19.7% | 2026-05-11 |
| MEDIC Benchmark | Medical | 71 | 55.71 average normalized public table score | 2026-05-27 |
| LanguageBench | Multilingual | 29 | 0.14 | 2026-05-06 |
| GPQA Diamond | Reasoning | 233 | 66.8% | 2026-05-11 |
| GPQA Diamond | Reasoning | 323 | 53.5% | 2026-05-11 |
| CritPt | Science | 148 | 0.3% | 2026-05-11 |
| SciPredict | Science | 9 | 17.04 | 2026-05-06 |
| K-MetBench | Weather | 46 | 47.5% accuracy | 2026-05-28 |
No matching rows.