OmniCorso-7B [float16] [rev: 3f9de5b67315]: benchmark results
A SLERP merge released by macadeliccc of mlabonne/OmniBeagle-7B and macadeliccc/MBX-7B-v3-DPO, using MBX as the base and separate attention and feed-forward interpolation schedules. Provider: macadeliccc. Access: Open.
Aggregate Rating 1464 ± 41, rank #3087 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 73.5 | MC2 (%) (0-shot) | 94.3 |
| Open LLM Leaderboard v1 - HellaSwag | 88.78 | Normalized accuracy (%) (10-shot) | 94 |
| Open LLM Leaderboard v1 - GSM8K | 70.51 | Accuracy (%) (5-shot) | 93.3 |
| Open LLM Leaderboard v1 - ARC Challenge | 72.44 | Normalized accuracy (%) (25-shot) | 92 |
| Open LLM Leaderboard v1 - WinoGrande | 83.5 | Accuracy (%) (5-shot) | 89.2 |
| Open LLM Leaderboard v1 - MMLU | 65.08 | Accuracy (%) (5-shot) | 81.4 |
Interactive version: theaggregate.ai/model?slug=omnicorso-7b-float16-rev-3f9de5b67315 · How It Works · Data refreshed daily, snapshot 2026-11-08.