Qwen3 14B
Qwen / Qwen
38scores
27benchmarks
$0.06 / $0.24 per 1M tokenscost in/out
Metadata
Qwen Open source
Aliases: qwen-qwen3-14b, qwen-qwen3-14b-04-28, qwen/qwen3-14b, qwen/qwen3-14b-04-28, qwen3-14b, qwen3-14b-04-28
| Benchmark | Category | Rank | Score | Sampled |
|---|---|---|---|---|
| AMA-Bench | Agentic | 7 | 0.46 | 2026-05-06 |
| Berkeley Function-Calling Leaderboard | Agentic | 43 | 41.03% | 2026-05-27 |
| Berkeley Function-Calling Leaderboard | Agentic | 47 | 37.77% | 2026-05-27 |
| Tau2-Bench Telecom | Agentic | 219 | 34.5% | 2026-05-11 |
| Tau2-Bench Telecom | Agentic | 230 | 32.2% | 2026-05-11 |
| Terminal-Bench Hard | Agentic | 264 | 5.3% | 2026-05-11 |
| Terminal-Bench Hard | Agentic | 293 | 3.8% | 2026-05-11 |
| OpenUGI | Alignment | 740 | 31.85 | 2026-05-06 |
| OpenUGI | Alignment | 753 | 31.46 | 2026-05-06 |
| SciCode | Coding | 233 | 31.6% | 2026-05-11 |
| SciCode | Coding | 306 | 26.5% | 2026-05-11 |
| Vectara HHEM Hallucination Leaderboard | Factuality | 17 | 94.60 | 2026-05-06 |
| BizFinBench | Finance | 11 | 67.05 | 2026-05-27 |
| Fin-RATE | Finance | 13 | 11.25% | 2026-05-28 |
| HealthBench Hard | Healthcare | 37 | 0.28 | 2026-05-27 |
| Artificial Analysis Intelligence Index | Intelligence | 297 | 16.19 | 2026-05-11 |
| Artificial Analysis Intelligence Index | Intelligence | 370 | 12.76 | 2026-05-11 |
| FACTS Grounding | Intelligence | 11 | 0.38 | 2026-05-06 |
| Humanity's Last Exam | Intelligence | 385 | 4.3% | 2026-05-11 |
| Humanity's Last Exam | Intelligence | 400 | 4.2% | 2026-05-11 |
| MMLU-Pro | Intelligence | 150 | 77.4% | 2026-05-11 |
| MMLU-Pro | Intelligence | 240 | 67.5% | 2026-05-11 |
| AraGen v3 | Language | 43 | 29.74 | 2026-05-06 |
| Open Arabic LLM Leaderboard | Language | 134 | 40.92 | 2026-05-06 |
| Open Portuguese LLM Leaderboard | Language | 52 | 85.52 | 2026-05-06 |
| J1-ENVS | Legal | 9 | 50.81 | 2026-05-26 |
| AIME 2025 | Math | 121 | 58% | 2026-05-11 |
| AIME 2025 | Math | 131 | 55.7% | 2026-05-11 |
| LiveMedBench | Medical | 13 | 0.1545 | 2026-05-27 |
| MEDIC Benchmark | Medical | 81 | 52.09 average normalized public table score | 2026-05-27 |
| Medmarks | Medical | 25 | 0.5366833465791869 | 2026-05-27 |
| FLORES European Languages Leaderboard | Multilingual | 6 | 45.64 | 2026-05-06 |
| INCLUDE-base-44 European Languages | Multilingual | 2 | 0.65 | 2026-05-06 |
| GPQA Diamond | Reasoning | 276 | 60.4% | 2026-05-11 |
| GPQA Diamond | Reasoning | 361 | 47% | 2026-05-11 |
| CritPt | Science | 343 | 0% | 2026-05-11 |
| CritPt | Science | 344 | 0% | 2026-05-11 |
| K-MetBench | Weather | 16 | 73.7% accuracy | 2026-05-28 |
No matching rows.