gemma-2B-sft-preview: benchmark results
Provider: Google. Access: API.
Aggregate Rating 1304 ± 36, rank #8664 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 38.59 | Accuracy (%) (5-shot) | 53.4 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 51.3 | MC2 (%) (0-shot) | 51.5 |
| Open LLM Leaderboard v1 - ARC Challenge | 52.3 | Normalized accuracy (%) (25-shot) | 26.9 |
| Open LLM Leaderboard v1 - MMLU | 45.83 | Accuracy (%) (5-shot) | 24.3 |
| Open LLM Leaderboard v1 - HellaSwag | 73.6 | Normalized accuracy (%) (10-shot) | 23.9 |
| Open LLM Leaderboard v1 - WinoGrande | 67.01 | Accuracy (%) (5-shot) | 21 |
Interactive version: theaggregate.ai/model?slug=gemma-2b-sft-preview · How It Works · Data refreshed daily, snapshot 2026-11-08.