flammen24-mistral-7B: benchmark results
A DPO fine-tune released by flammen.ai of flammenai/flammen23X-mistral-7B, using jondurbin/truthy-dpo-v0.1. Provider: flammen.ai. Access: Open.
Aggregate Rating 1443 ± 36, rank #4081 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 73.51 | MC2 (%) (0-shot) | 94.3 |
| Open LLM Leaderboard v1 - HellaSwag | 86.85 | Normalized accuracy (%) (10-shot) | 83.3 |
| Open LLM Leaderboard v1 - GSM8K | 66.03 | Accuracy (%) (5-shot) | 81.1 |
| Open LLM Leaderboard v1 - ARC Challenge | 68.52 | Normalized accuracy (%) (25-shot) | 80.6 |
| Open LLM Leaderboard v1 - WinoGrande | 80.74 | Accuracy (%) (5-shot) | 75.4 |
| Open LLM Leaderboard v1 - MMLU | 64.62 | Accuracy (%) (5-shot) | 73.5 |
Interactive version: theaggregate.ai/model?slug=flammen24-mistral-7b · How It Works · Data refreshed daily, snapshot 2026-11-08.