starcoder-finetune-selfinstruct: benchmark results
Provider: BigCode.
Aggregate Rating 1163 ± 35, rank #9806 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 6.07 | Accuracy (%) (5-shot) | 25.1 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 41.63 | MC2 (%) (0-shot) | 17.7 |
| Open LLM Leaderboard v1 - MMLU | 29.52 | Accuracy (%) (5-shot) | 16.4 |
| Open LLM Leaderboard v1 - WinoGrande | 57.77 | Accuracy (%) (5-shot) | 11 |
| Open LLM Leaderboard v1 - ARC Challenge | 31.23 | Normalized accuracy (%) (25-shot) | 10.1 |
| Open LLM Leaderboard v1 - HellaSwag | 47.66 | Normalized accuracy (%) (10-shot) | 9.6 |
Interactive version: theaggregate.ai/model?slug=starcoder-finetune-selfinstruct · How It Works · Data refreshed daily, snapshot 2026-11-08.