gemma-2B-zephyr-dpo (Publisher: wandb): benchmark results
Provider: Google. Access: API.
Aggregate Rating 1269 ± 35, rank #9073 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 17.51 | Accuracy (%) (5-shot) | 39 |
| Open LLM Leaderboard v1 - ARC Challenge | 49.66 | Normalized accuracy (%) (25-shot) | 24.2 |
| Open LLM Leaderboard v1 - HellaSwag | 72.23 | Normalized accuracy (%) (10-shot) | 22.6 |
| Open LLM Leaderboard v1 - MMLU | 41.13 | Accuracy (%) (5-shot) | 21.5 |
| Open LLM Leaderboard v1 - WinoGrande | 66.54 | Accuracy (%) (5-shot) | 20.4 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 34.47 | MC2 (%) (0-shot) | 1.2 |
Interactive version: theaggregate.ai/model?slug=gemma-2b-zephyr-dpo-publisher-wandb · How It Works · Data refreshed daily, snapshot 2026-11-08.