Qwen3-4B-Base
Qwen3-4B-Base.
10
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Qwen3-4B-Base
Open weights Small
No Epoch Capabilities Index score yet
- Alyah 27.4% #12 /16
- BLUEX 45.3% #127 /177
- HeQ 67.8% #40 /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 | 54.9% | #9 of 52 | Official leaderboard | |
| Open Hebrew LLM Leaderboard | 53.1 | #38 of 88 | Official leaderboard | |
| 3LM | 74.7% | #11 of 25 | Official leaderboard | |
| HeQ | 67.8% | #40 of 88 | Official leaderboard | |
| MultiBLiMP | 83.7% | #12 of 25 | Official leaderboard | |
| Uncheatable Eval | 7.46 | #19 of 33 | Official leaderboard | |
| Open Portuguese LLM Leaderboard | 63.6 | #105 of 175 | Official leaderboard | |
| NorEval | 48.0 | #13 of 19 | Official leaderboard | |
| BLUEX | 45.3% | #127 of 177 | Official leaderboard | |
| Alyah | 27.4% | #12 of 16 | 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