Rabbit-7B-v2-DPO-Chat: benchmark results
Provider: Other. Access: Open.
Aggregate Rating 1424 ± 35, rank #4973 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 67.06 | MC2 (%) (0-shot) | 85.4 |
| Open LLM Leaderboard v1 - ARC Challenge | 66.13 | Normalized accuracy (%) (25-shot) | 72.4 |
| Open LLM Leaderboard v1 - HellaSwag | 85.18 | Normalized accuracy (%) (10-shot) | 72.4 |
| Open LLM Leaderboard v1 - WinoGrande | 79.24 | Accuracy (%) (5-shot) | 68.1 |
| Open LLM Leaderboard v1 - GSM8K | 55.65 | Accuracy (%) (5-shot) | 67.3 |
| Open LLM Leaderboard v1 - MMLU | 62.92 | Accuracy (%) (5-shot) | 57.4 |
Interactive version: theaggregate.ai/model?slug=rabbit-7b-v2-dpo-chat · How It Works · Data refreshed daily, snapshot 2026-11-08.