Deita-4B: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1331 ± 39, rank #8143 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 48.9 | Accuracy (%) (5-shot) | 61.9 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 50.23 | MC2 (%) (0-shot) | 47.7 |
| Open LLM Leaderboard v1 - MMLU | 55.46 | Accuracy (%) (5-shot) | 36.3 |
| Open LLM Leaderboard v1 - HellaSwag | 71.81 | Normalized accuracy (%) (10-shot) | 22 |
| Open LLM Leaderboard v1 - ARC Challenge | 46.08 | Normalized accuracy (%) (25-shot) | 21.3 |
| Open LLM Leaderboard v1 - WinoGrande | 66.14 | Accuracy (%) (5-shot) | 19.8 |
Interactive version: theaggregate.ai/model?slug=deita-4b · How It Works · Data refreshed daily, snapshot 2026-11-08.