NeuralSynthesis-7B-v0.4-slerp: benchmark results
Kukedlc's NeuralSynthesis 7B v0.4, a LazyMergekit SLERP merge of allknowingroger's MultiverseEx26-7B-slerp and their own NeuralSynthesis-7B-v0.1. Provider: Kukedlc. Released 2024-04-12. Access: Open.
Aggregate Rating 1450 ± 22, rank #998 of 1656 rated models, from 31 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 78.07 | MC2 (%) (0-shot) | 98.3 |
| Open LLM Leaderboard v1 - HellaSwag | 89.14 | Normalized accuracy (%) (10-shot) | 97.7 |
| Open LLM Leaderboard v1 - ARC Challenge | 73.21 | Normalized accuracy (%) (25-shot) | 96.3 |
| Open LLM Leaderboard v1 - WinoGrande | 84.85 | Accuracy (%) (5-shot) | 95.5 |
| Open LLM Leaderboard v1 - GSM8K | 71.04 | Accuracy (%) (5-shot) | 95 |
| Open Chinese LLM - TruthfulQA MC | 63.44 | Accuracy (%) | 93.2 |
| Open Portuguese LLM - FaQuAD NLI | 77.86 | Macro F1 (%) | 81.7 |
| Open Portuguese LLM - ASSIN2 RTE | 92.32 | Macro F1 (%) | 77.6 |
| Open LLM Leaderboard - MuSR | 43.32 | Score | 73 |
| Open LLM Leaderboard v1 - MMLU | 64.28 | Accuracy (%) (5-shot) | 67.5 |
| Open Chinese LLM - ARC Challenge | 54.01 | Accuracy (%) | 62 |
| Open Portuguese LLM - BLUEX | 54.52 | Accuracy (%) | 60.4 |
Interactive version: theaggregate.ai/model?slug=neuralsynthesis-7b-v0-4-slerp · How It Works · Data refreshed daily, snapshot 2026-10-20.