gemma-3.5B-orpo-selfmerge: benchmark results
Provider: Google. Access: API.
Aggregate Rating 1214 ± 34, rank #9520 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 44.96 | MC2 (%) (0-shot) | 29.2 |
| Open LLM Leaderboard v1 - GSM8K | 4.25 | Accuracy (%) (5-shot) | 22.6 |
| Open LLM Leaderboard v1 - ARC Challenge | 43.69 | Normalized accuracy (%) (25-shot) | 19.4 |
| Open LLM Leaderboard v1 - MMLU | 34.47 | Accuracy (%) (5-shot) | 18.1 |
| Open LLM Leaderboard v1 - HellaSwag | 64.53 | Normalized accuracy (%) (10-shot) | 16.9 |
| Open LLM Leaderboard v1 - WinoGrande | 59.27 | Accuracy (%) (5-shot) | 12.4 |
Interactive version: theaggregate.ai/model?slug=gemma-3-5b-orpo-selfmerge · How It Works · Data refreshed daily, snapshot 2026-11-08.