Qwen2.5-0.5B
Qwen2.5-0.5B places in the top three on Vectara Hallucination Leaderboard (HHEM).
14
Benchmarks with a score
0
Ranked first, out of five or more models
1
In the top three
Qwen Sep 2024 Qwen2.5-0.5B
Open weights Small
No Epoch Capabilities Index score yet
- Vectara Hallucination Leaderboard (HHEM) 25.2% #2 /148
- BigCodeBench-Hard 1.40% #95 /96
- AlGhafa 40.4% #34 /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 | |
|---|---|---|---|---|
| Vectara Hallucination Leaderboard (HHEM) | 25.2% | #2 of 148 | Official leaderboard | |
| ArbMMLU-HT | 27.9% | #30 of 39 | Official leaderboard | |
| AlGhafa | 40.4% | #34 of 39 | Official leaderboard | |
| ArabicMMLU | 30.5% | #34 of 39 | Official leaderboard | |
| ALRAGE | 42.6% | #36 of 39 | Official leaderboard | |
| Open Arabic LLM Leaderboard v2 | 34.2% | #36 of 39 | Official leaderboard | |
| MMLU-CF | 41.9% | #35 of 37 | Official leaderboard | |
| MMLU-Pro | 14.9% | #203 of 212 | Official leaderboard | |
| MadinahQA | 24.8% | #38 of 39 | Official leaderboard | |
| SuperGPQA | 10.8% | #58 of 58 | Official leaderboard | |
| FaithJudge | 76.3% | #37 of 37 | Official leaderboard |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| BigCodeBench | 10.1% | #67 of 69 | Official leaderboard | |
| BigCodeBench-Hard | 1.40% | #95 of 96 | Official leaderboard |
Safety and security
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| AraTrust | 47.3% | #31 of 39 | Official leaderboard |