Zephyr 7B Beta
Zephyr 7B Beta.
11
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Hugging Face Oct 2023 Zephyr 7B Beta
Open weights Small
No Epoch Capabilities Index score yet
- Ko-IFEval (Upstage) 30% #16 /21
- CyberMetric 65% #4 /10
- RewardBench 72.8% #39 /48
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 | |
|---|---|---|---|---|
| AlpacaEval | 90.6% | #10 of 19 | Official leaderboard | |
| Ko-IFEval (Upstage) | 30% | #16 of 21 | Official leaderboard | |
| AlpacaEval 2.0 | 13.2% | #36 of 47 | Official leaderboard | |
| EQ-Bench v2 | 58.3 | #69 of 85 | Official leaderboard | |
| RewardBench | 72.8% | #39 of 48 | Official leaderboard | |
| MMLU-Pro | 33% | #176 of 212 | Official leaderboard | |
| LMArena (Elo) | 1,131 | #315 of 335 | Official leaderboard |
Safety and security
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| PrivacyLens | 19.3% | #1 of 4 | Official leaderboard | |
| CyberMetric | 65% | #4 of 10 | Official leaderboard | |
| SORRY-Bench | 87.5% | #22 of 23 | Official leaderboard | |
| DecodingTrust | 63.2 | #5 of 5 | Official leaderboard |