Mnemosyne-7B: benchmark results
Provider: bunnycore. Access: Open.
Aggregate Rating 1415 ± 30, rank #5416 of 10916 rated models, from 12 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 62.67 | MC2 (%) (0-shot) | 79.5 |
| Open LLM Leaderboard v1 - ARC Challenge | 65.44 | Normalized accuracy (%) (25-shot) | 70 |
| Open LLM Leaderboard v1 - HellaSwag | 84.72 | Normalized accuracy (%) (10-shot) | 68 |
| Open LLM Leaderboard v1 - WinoGrande | 78.93 | Accuracy (%) (5-shot) | 66.3 |
| Open LLM Leaderboard v1 - GSM8K | 52.08 | Accuracy (%) (5-shot) | 64 |
| Open CoT - LSAT Logical Reasoning | 12.75 | CoT Gain (%) | 62.2 |
| Open CoT - LSAT Analytical Reasoning | 4.35 | CoT Gain (%) | 56.9 |
| Open LLM Leaderboard v1 - MMLU | 62.49 | Accuracy (%) (5-shot) | 55.4 |
| Open CoT Leaderboard | 7.68 | Average CoT Gain (%) | 54.2 |
| Open CoT - LogiQA 2 | 6.74 | CoT Gain (%) | 50.4 |
| Open CoT - LSAT Reading Comprehension | 11.52 | CoT Gain (%) | 49.6 |
| Open CoT - LogiQA | 3.04 | CoT Gain (%) | 37.8 |
Interactive version: theaggregate.ai/model?slug=mnemosyne-7b · How It Works · Data refreshed daily, snapshot 2026-11-08.