HelpingAI-3B: benchmark results
Provider: Other.
Aggregate Rating 1308 ± 36, rank #8589 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 55.62 | MC2 (%) (0-shot) | 65.6 |
| Open LLM Leaderboard v1 - GSM8K | 36.09 | Accuracy (%) (5-shot) | 51.6 |
| Open LLM Leaderboard v1 - HellaSwag | 76.64 | Normalized accuracy (%) (10-shot) | 29.2 |
| Open LLM Leaderboard v1 - MMLU | 46.82 | Accuracy (%) (5-shot) | 25.6 |
| Open LLM Leaderboard v1 - ARC Challenge | 50.6 | Normalized accuracy (%) (25-shot) | 24.9 |
| Open LLM Leaderboard v1 - WinoGrande | 67.8 | Accuracy (%) (5-shot) | 21.7 |
Interactive version: theaggregate.ai/model?slug=helpingai-3b · How It Works · Data refreshed daily, snapshot 2026-11-08.