Mahou-1.0-mistral-7B: benchmark results
A DPO fine-tune released by flammen.ai of flammenai/flammen24-mistral-7B, using flammenai/FlameMix-DPO-v1. The release targets casual conversation and character roleplay. Provider: flammen.ai. Access: Open.
Aggregate Rating 1439 ± 36, rank #4245 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 72.42 | MC2 (%) (0-shot) | 93.5 |
| Open LLM Leaderboard v1 - HellaSwag | 86.52 | Normalized accuracy (%) (10-shot) | 81.6 |
| Open LLM Leaderboard v1 - GSM8K | 64.29 | Accuracy (%) (5-shot) | 78 |
| Open LLM Leaderboard v1 - WinoGrande | 81.06 | Accuracy (%) (5-shot) | 77 |
| Open LLM Leaderboard v1 - ARC Challenge | 67.41 | Normalized accuracy (%) (25-shot) | 76.7 |
| Open LLM Leaderboard v1 - MMLU | 64.16 | Accuracy (%) (5-shot) | 66.3 |
Interactive version: theaggregate.ai/model?slug=mahou-1-0-mistral-7b · How It Works · Data refreshed daily, snapshot 2026-11-08.