PowerLM-3B: benchmark results
Provider: Other. Access: Open.
Unified ELO 1401 ± 1, rank #1130 of 1392 rated models, from 12 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Enkrypt AI - Bias Risk | 62.53 | Risk Score | 83.7 |
| Open LLM Leaderboard - IFEval | 33.21 | Score | 31.1 |
| Open LLM Leaderboard - GPQA | 3.36 | Score | 30.3 |
| Open LLM Leaderboard - MuSR | 5.64 | Score | 27.3 |
| Open LLM Leaderboard - MMLU-Pro | 11.29 | Score | 21.7 |
| Enkrypt AI - Insecure Code Risk | 54.22 | Risk Score | 21.2 |
| Open LLM Leaderboard - BBH | 12.02 | Score | 21.2 |
| Open LLM Leaderboard - MATH Level 5 | 3.63 | Score | 21.2 |
| Enkrypt AI - Risk Score | 49.4 | Risk Score | 9.1 |
| Enkrypt AI - Safety Risk | 44.04 | Risk Score | 7.6 |
| Enkrypt AI - Jailbreak Risk | 41.41 | Risk Score | 1.5 |
| Enkrypt AI - Toxicity Risk | 42.73 | Risk Score | 1.1 |
Interactive version: theaggregate.ai/model?slug=powerlm-3b · How It Works · Data refreshed daily, snapshot 2026-09-05.