Qwen1.5-14B-Chat
Qwen1.5-14B-Chat places in the top three on SALAD-Bench.
13
Benchmarks with a score
0
Ranked first, out of five or more models
1
In the top three
Qwen Feb 2024 Qwen1.5-14B-Chat
Open weights Mid-size
No Epoch Capabilities Index score yet
- Open Arabic LLM Leaderboard v1 47.1% #19 /55
- Ko-IFEval (Upstage) 40.1% #7 /21
- CFBench 49.8% #9 /19
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 | 44% | #25 of 98 | Official leaderboard | |
| Ko-IFEval (Upstage) | 40.1% | #7 of 21 | Official leaderboard | |
| Open Arabic LLM Leaderboard v1 | 47.1% | #19 of 55 | Official leaderboard | |
| EQ-Bench v2 | 75.0 | #38 of 85 | Official leaderboard | |
| CFBench | 49.8% | #9 of 19 | Official leaderboard | |
| AlpacaEval 2.0 | 23.9% | #23 of 47 | Official leaderboard | |
| MMLU-Pro | 38% | #167 of 212 | Official leaderboard | |
| RepoQA | 26% | #19 of 22 | Official leaderboard | |
| RewardBench | 68.6% | #43 of 48 | Official leaderboard |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| GTA | 12.4% | #7 of 15 | Official leaderboard |
Safety and security
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| SALAD-Bench | 95.4% | #3 of 13 | Official leaderboard | |
| SORRY-Bench | 33.9% | #15 of 23 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Open LLM Leaderboard v2 | 23.6 | #46 of 99 | Official leaderboard |