Mahou-1.3-mistral-7B: benchmark results
A ORPO fine-tune released by flammen.ai of nbeerbower/Flammen-Mahou-mistral-7B, using flammenai/MahouMix-v1. The release targets casual conversation and character roleplay. Its card specifies ChatML prompting. Provider: flammen.ai. Access: Open.
Aggregate Rating 1442 ± 36, rank #4119 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 67.59 | MC2 (%) (0-shot) | 86.2 |
| Open LLM Leaderboard v1 - HellaSwag | 87.29 | Normalized accuracy (%) (10-shot) | 85.3 |
| Open LLM Leaderboard v1 - ARC Challenge | 70.05 | Normalized accuracy (%) (25-shot) | 84.9 |
| Open LLM Leaderboard v1 - MMLU | 64.57 | Accuracy (%) (5-shot) | 72.7 |
| Open LLM Leaderboard v1 - WinoGrande | 80.03 | Accuracy (%) (5-shot) | 72 |
| Open LLM Leaderboard v1 - GSM8K | 58.07 | Accuracy (%) (5-shot) | 69.7 |
Interactive version: theaggregate.ai/model?slug=mahou-1-3-mistral-7b · How It Works · Data refreshed daily, snapshot 2026-11-08.