Qwen2-0.5B-Instruct
Qwen2-0.5B-Instruct.
10
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Qwen Jun 2024 Qwen2-0.5B-Instruct
Open weights Small
No Epoch Capabilities Index score yet
- KOR-Bench 3.52% #33 /33
- AlGhafa 40.6% #33 /39
- ALRAGE 38.5% #37 /39
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 | |
|---|---|---|---|---|
| ArabicMMLU | 36.5% | #27 of 39 | Official leaderboard | |
| ArbMMLU-HT | 29.6% | #28 of 39 | Official leaderboard | |
| AlGhafa | 40.6% | #33 of 39 | Official leaderboard | |
| Open Arabic LLM Leaderboard v2 | 35.6% | #33 of 39 | Official leaderboard | |
| MadinahQA | 28.2% | #34 of 39 | Official leaderboard | |
| MMLU-Pro | 15.9% | #199 of 212 | Official leaderboard | |
| ALRAGE | 38.5% | #37 of 39 | Official leaderboard | |
| MMLU-CF | 38.3% | #37 of 37 | Official leaderboard |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| KOR-Bench | 3.52% | #33 of 33 | Official leaderboard |
Safety and security
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| AraTrust | 46.9% | #32 of 39 | Official leaderboard |