gemma-3B-002: benchmark results
Provider: Google. Access: API.
Aggregate Rating 1225 ± 33, rank #9448 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 5.53 | Accuracy (%) (5-shot) | 24.3 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 42.68 | MC2 (%) (0-shot) | 21.3 |
| Open LLM Leaderboard v1 - ARC Challenge | 43.34 | Normalized accuracy (%) (25-shot) | 19.1 |
| Open LLM Leaderboard v1 - MMLU | 36.86 | Accuracy (%) (5-shot) | 18.9 |
| Open LLM Leaderboard v1 - HellaSwag | 64.06 | Normalized accuracy (%) (10-shot) | 16.7 |
| Open LLM Leaderboard v1 - WinoGrande | 60.85 | Accuracy (%) (5-shot) | 13.9 |
Interactive version: theaggregate.ai/model?slug=gemma-3b-002 · How It Works · Data refreshed daily, snapshot 2026-11-08.