Qwen1.5-4B-Chat
Qwen1.5-4B-Chat places in the top three on SALAD-Bench.
10
Benchmarks with a score
0
Ranked first, out of five or more models
1
In the top three
Qwen Feb 2024 Qwen1.5-4B-Chat
Open weights Small
No Epoch Capabilities Index score yet
- Open Arabic LLM Leaderboard v1 37.3% #46 /55
- CFBench 28% #13 /19
- SALAD-Bench 95.5% #2 /13
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 | |
|---|---|---|---|---|
| MuSR | 39.8% | #58 of 98 | Official leaderboard | |
| CFBench | 28% | #13 of 19 | Official leaderboard | |
| Open Arabic LLM Leaderboard v1 | 37.3% | #46 of 55 | Official leaderboard | |
| MixEval | 57.2% | #32 of 34 | Official leaderboard | |
| EQ-Bench v2 | 28.8 | #82 of 85 | Official leaderboard | |
| LMArena (Elo) | 1,091 | #326 of 335 | Official leaderboard | |
| RewardBench | 54.8% | #48 of 48 | Official leaderboard |
Safety and security
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| SALAD-Bench | 95.5% | #2 of 13 | Official leaderboard | |
| SORRY-Bench | 26.6% | #11 of 23 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Open LLM Leaderboard v2 | 12.6 | #82 of 99 | Official leaderboard |