Qwen3-14B-Base
Qwen3-14B-Base ranks first on NOVA-63.
10
Benchmarks with a score
1
Ranked first, out of five or more models
1
In the top three
Qwen3-14B-Base
Open weights Mid-size
No Epoch Capabilities Index score yet
- Alyah 57.3% #9 /16
- BLUEX 51.5% #107 /177
- HeQ 80.9% #15 /88
Where it ranks
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.
Knowledge and language
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| NOVA-63 | 61.3% | #1 of 52 | Official leaderboard | |
| MultiBLiMP | 87.4% | #4 of 25 | Official leaderboard | |
| HeQ | 80.9% | #15 of 88 | Official leaderboard | |
| Open Hebrew LLM Leaderboard | 63.0 | #18 of 88 | Official leaderboard | |
| Uncheatable Eval | 6.82 | #8 of 33 | Official leaderboard | |
| 3LM | 80.4% | #7 of 25 | Official leaderboard | |
| NorEval | 55.2 | #8 of 19 | Official leaderboard | |
| Open Portuguese LLM Leaderboard | 66.8 | #90 of 175 | Official leaderboard | |
| Alyah | 57.3% | #9 of 16 | Official leaderboard | |
| BLUEX | 51.5% | #107 of 177 | Official leaderboard |
Who measured it?
Independent runs cover all 10 of its benchmarks.
- An independent run only 10
Sources: Official leaderboards, Epoch AI (CC BY 4.0) and labs’ model cards