Mahou-1.1-mistral-7B: benchmark results
A DPO fine-tune released by flammen.ai of flammenai/Mahou-1.0-mistral-7B, using flammenai/Grill-preprod-v1_chatML. The release targets casual conversation and character roleplay. Its card specifies ChatML prompting. Provider: flammen.ai. Access: Open.
Aggregate Rating 1434 ± 35, rank #4472 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 72.7 | MC2 (%) (0-shot) | 93.8 |
| Open LLM Leaderboard v1 - HellaSwag | 86.65 | Normalized accuracy (%) (10-shot) | 82.1 |
| Open LLM Leaderboard v1 - ARC Challenge | 66.72 | Normalized accuracy (%) (25-shot) | 74.5 |
| Open LLM Leaderboard v1 - GSM8K | 60.8 | Accuracy (%) (5-shot) | 73 |
| Open LLM Leaderboard v1 - WinoGrande | 79.79 | Accuracy (%) (5-shot) | 71 |
| Open LLM Leaderboard v1 - MMLU | 64.28 | Accuracy (%) (5-shot) | 67.5 |
Interactive version: theaggregate.ai/model?slug=mahou-1-1-mistral-7b · How It Works · Data refreshed daily, snapshot 2026-11-08.