smaug-mini: benchmark results
Provider: Abacus.AI. Access: Open.
Aggregate Rating 1763 ± 43, rank #151 of 10916 rated models, from 23 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| LiveBench Python | 70 | Score | 91.4 |
| LiveBench Story Generation | 78 | Score | 90 |
| LiveBench Paraphrase | 76.18 | Score | 87.1 |
| LiveBench Table Join | 51.87 | Score | 85.7 |
| LiveBench TypeScript | 53.33 | Score | 85 |
| LiveBench Summarize | 76.1 | Score | 77.1 |
| LiveBench Typos | 84 | Score | 73.6 |
| LiveBench Code Completion | 80.44 | Score | 70 |
| LiveBench Consecutive Events | 88.5 | Score | 65.7 |
| LiveBench Spatial | 98 | Score | 60.7 |
| LiveBench AMPS Hard | 98 | Score | 58.6 |
| LiveBench Olympiad | 90.85 | Score | 55.7 |
Interactive version: theaggregate.ai/model?slug=smaug-mini · How It Works · Data refreshed daily, snapshot 2026-11-08.