Mahou-1.2-mistral-7B: benchmark results
A DPO fine-tune released by flammen.ai of flammenai/flammen25-mistral-7B, using flammenai/Grill-preprod-v1_chatML, flammenai/Grill-preprod-v2_chatML. The release targets casual conversation and character roleplay. Its card specifies ChatML prompting. Provider: flammen.ai. Access: Open.
Aggregate Rating 1435 ± 35, rank #4401 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 71.33 | MC2 (%) (0-shot) | 91.6 |
| Open LLM Leaderboard v1 - HellaSwag | 86.98 | Normalized accuracy (%) (10-shot) | 83.9 |
| Open LLM Leaderboard v1 - ARC Challenge | 67.41 | Normalized accuracy (%) (25-shot) | 76.7 |
| Open LLM Leaderboard v1 - MMLU | 64.56 | Accuracy (%) (5-shot) | 72.5 |
| Open LLM Leaderboard v1 - GSM8K | 59.36 | Accuracy (%) (5-shot) | 71.2 |
| Open LLM Leaderboard v1 - WinoGrande | 79.01 | Accuracy (%) (5-shot) | 66.7 |
Interactive version: theaggregate.ai/model?slug=mahou-1-2-mistral-7b · How It Works · Data refreshed daily, snapshot 2026-11-08.