Qwen1.5-32B
Qwen1.5-32B.
Qwen Released 4 Feb 2024 16
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Qwen Feb 2024 Qwen1.5-32B
Open weights
No Epoch Capabilities Index score yet
- GPQA Diamond 30.7% #196 /219
- AlGhafa 66.4% #15 /39
- ALRAGE 67% #23 /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 | |
|---|---|---|---|---|
| MadinahQA | 53% | #11 of 39 | Official leaderboard | |
| MMLU | 74.4% | #42 of 127 | Epoch AI | |
| Open Arabic LLM Leaderboard v2 | 56.2% | #14 of 39 | Official leaderboard | |
| AlGhafa | 66.4% | #15 of 39 | Official leaderboard | |
| EQ-Bench v2 | 75.6 | #36 of 85 | Official leaderboard | |
| ArbMMLU-HT | 45.3% | #17 of 39 | Official leaderboard | |
| ArabicMMLU | 48.8% | #20 of 39 | Official leaderboard | |
| MixEval | 81% | #19 of 34 | Official leaderboard | |
| ALRAGE | 67% | #23 of 39 | Official leaderboard | |
| LMArena (Elo) | 1,204 | #281 of 333 | Official leaderboard |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| OlympicArena | 24.4% | #11 of 25 | Official leaderboard | |
| GPQA Diamond | 30.7% | #196 of 219 | Epoch AI |
Safety and security
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| HELM Lite | 54.6 | #33 of 71 | Official leaderboard | |
| Political Science LLM Benchmark | 61.9% | #27 of 29 | Official leaderboard |