flammen27-mistral-7B: benchmark results
A SLERP merge released by flammen.ai of InferenceIllusionist/Excalibur-7b and flammen26-mistral-7B, using different interpolation schedules for attention and feed-forward tensors. Provider: flammen.ai. Access: Open.
Aggregate Rating 1450 ± 37, rank #3760 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 68.87 | MC2 (%) (0-shot) | 88.2 |
| Open LLM Leaderboard v1 - HellaSwag | 87.39 | Normalized accuracy (%) (10-shot) | 86 |
| Open LLM Leaderboard v1 - ARC Challenge | 69.8 | Normalized accuracy (%) (25-shot) | 84.3 |
| Open LLM Leaderboard v1 - GSM8K | 67.48 | Accuracy (%) (5-shot) | 83.7 |
| Open LLM Leaderboard v1 - WinoGrande | 81.69 | Accuracy (%) (5-shot) | 80.5 |
| Open LLM Leaderboard v1 - MMLU | 65.01 | Accuracy (%) (5-shot) | 80.3 |
Interactive version: theaggregate.ai/model?slug=flammen27-mistral-7b · How It Works · Data refreshed daily, snapshot 2026-11-08.