MultiverseEx26-7B-slerp: benchmark results
allknowingroger's SLERP merge of MTSAIR's multi_verse_model with yam-peleg's Experiment26-7B, two high-scoring Mistral leaderboard fine-tunes. Provider: Other. Released 2024-03-31.
Aggregate Rating 1466 ± 23, rank #904 of 1656 rated models, from 25 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 78.12 | MC2 (%) (0-shot) | 98.5 |
| Open LLM Leaderboard v1 - HellaSwag | 89.17 | Normalized accuracy (%) (10-shot) | 98.2 |
| Open LLM Leaderboard v1 - WinoGrande | 85.16 | Accuracy (%) (5-shot) | 97.5 |
| Open LLM Leaderboard v1 - GSM8K | 71.04 | Accuracy (%) (5-shot) | 95 |
| Open LLM Leaderboard v1 - ARC Challenge | 72.95 | Normalized accuracy (%) (25-shot) | 94.5 |
| Open Chinese LLM - TruthfulQA MC | 63.61 | Accuracy (%) | 93.5 |
| Open Portuguese LLM - FaQuAD NLI | 78.42 | Macro F1 (%) | 84 |
| Open Portuguese LLM - ASSIN2 RTE | 92.24 | Macro F1 (%) | 76.6 |
| Open LLM Leaderboard - MuSR | 42.93 | Score | 69.9 |
| Open LLM Leaderboard v1 - MMLU | 64.36 | Accuracy (%) (5-shot) | 68.8 |
| Open Portuguese LLM - BLUEX | 54.38 | Accuracy (%) | 59.8 |
| Open Chinese LLM - WinoGrande | 63.46 | Accuracy (%) | 57.1 |
Interactive version: theaggregate.ai/model?slug=multiverseex26-7b-slerp · How It Works · Data refreshed daily, snapshot 2026-10-20.