Blur-7B-slerp-v1.41: benchmark results
liminerity's Blur-7b-slerp-v1.41 is a SLERP merge of bardsai/jaskier-7b-dpo-v5.6, liminerity/merge. The released configuration uses 32 mistral decoder layers; merge recipe dtype is not a measured evaluator precision. Provider: liminerity. Access: Open.
Aggregate Rating 1465 ± 42, rank #3017 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - GSM8K | 71.49 | Accuracy (%) (5-shot) | 96 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 74.23 | MC2 (%) (0-shot) | 94.8 |
| Open LLM Leaderboard v1 - ARC Challenge | 72.78 | Normalized accuracy (%) (25-shot) | 93.5 |
| Open LLM Leaderboard v1 - HellaSwag | 88.65 | Normalized accuracy (%) (10-shot) | 93.4 |
| Open LLM Leaderboard v1 - WinoGrande | 83.9 | Accuracy (%) (5-shot) | 91.1 |
| Open LLM Leaderboard v1 - MMLU | 64.84 | Accuracy (%) (5-shot) | 77.3 |
Interactive version: theaggregate.ai/model?slug=blur-7b-slerp-v1-41 · How It Works · Data refreshed daily, snapshot 2026-11-08.