Starling-LM-11B-alpha (Publisher: CallComply): benchmark results
Provider: UC Berkeley.
Aggregate Rating 1392 ± 33, rank #6453 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - WinoGrande | 78.06 | Accuracy (%) (5-shot) | 60.4 |
| Open LLM Leaderboard v1 - ARC Challenge | 61.26 | Normalized accuracy (%) (25-shot) | 52 |
| Open LLM Leaderboard v1 - MMLU | 61.5 | Accuracy (%) (5-shot) | 51.9 |
| Open LLM Leaderboard v1 - GSM8K | 35.18 | Accuracy (%) (5-shot) | 50.9 |
| Open LLM Leaderboard v1 - HellaSwag | 81.99 | Normalized accuracy (%) (10-shot) | 48.2 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 41.53 | MC2 (%) (0-shot) | 17.3 |
Interactive version: theaggregate.ai/model?slug=starling-lm-11b-alpha-publisher-callcomply · How It Works · Data refreshed daily, snapshot 2026-11-08.