SLM Trustworthiness - Machine Ethics: leaderboard
Metric: TrustLLM machine-ethics accuracy (%; sub-task mean). Source: arxiv.org. 11 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 2.5 7B Instruct | 83.78 |
| 2 | Llama 3.2 3B Instruct | 82.88 |
| 3 | Gemma 1.1 7B (IT) | 82.19 |
| 4 | Llama 3.1 8B Instruct | 81.29 |
| 5 | Qwen 2.5 3B Instruct | 80.13 |
| 6 | Qwen 2.5 1.5B Instruct | 77.52 |
| 7 | Llama 3.2 1B Instruct | 73.98 |
| 8 | Qwen 2.5 0.5B Instruct | 65.71 |
| 9 | h2o-danube3-500m-chat | 61.92 |
| 10 | SmolLM2-360M-Instruct | 51.47 |
Interactive version: theaggregate.ai/benchmark?slug=slm-trustworthiness-machine-ethics · How It Works · Data refreshed daily, snapshot 2026-09-19.