flammen29-mistral-7B: benchmark results
A ORPO fine-tune released by flammen.ai of flammenai/flammen27-mistral-7B, using flammenai/FlameMix-DPO-v1, flammenai/Grill-preprod-v1_chatML, flammenai/Grill-preprod-v2_chatML, flammenai/Grill-Flammen-v1_chatML. Provider: flammen.ai. Access: Open.
Aggregate Rating 1446 ± 36, rank #3922 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 65.84 | MC2 (%) (0-shot) | 84.2 |
| Open LLM Leaderboard v1 - GSM8K | 67.02 | Accuracy (%) (5-shot) | 82.8 |
| Open LLM Leaderboard v1 - ARC Challenge | 69.2 | Normalized accuracy (%) (25-shot) | 82.5 |
| Open LLM Leaderboard v1 - HellaSwag | 86.35 | Normalized accuracy (%) (10-shot) | 80.4 |
| Open LLM Leaderboard v1 - WinoGrande | 81.61 | Accuracy (%) (5-shot) | 80.1 |
| Open LLM Leaderboard v1 - MMLU | 64.79 | Accuracy (%) (5-shot) | 76.6 |
Interactive version: theaggregate.ai/model?slug=flammen29-mistral-7b · How It Works · Data refreshed daily, snapshot 2026-11-08.