gemma-2B-coder: benchmark results
Provider: Google. Access: API.
Aggregate Rating 1252 ± 37, rank #9239 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 16.07 | Accuracy (%) (5-shot) | 37.9 |
| Open LLM Leaderboard v1 - ARC Challenge | 48.98 | Normalized accuracy (%) (25-shot) | 23.6 |
| Open LLM Leaderboard v1 - HellaSwag | 71.43 | Normalized accuracy (%) (10-shot) | 21.6 |
| Open LLM Leaderboard v1 - WinoGrande | 66.85 | Accuracy (%) (5-shot) | 20.8 |
| Open LLM Leaderboard v1 - MMLU | 37.02 | Accuracy (%) (5-shot) | 19 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 33.54 | MC2 (%) (0-shot) | 0.6 |
Interactive version: theaggregate.ai/model?slug=gemma-2b-coder · How It Works · Data refreshed daily, snapshot 2026-11-08.