BurningBruce-SOLAR-8x10.7B-bf16: benchmark results
Kquant03's mixture-of-experts release whose published Mixtral configuration specifies 8 local experts, 2 selected per token and 48 decoder layers. Its recipe names kyujinpy/Sakura-SOLAR-Instruct as the base; nominal expert sizes are not measured total or active parameter counts. Provider: Kquant03. Access: Open.
Aggregate Rating 1456 ± 36, rank #3505 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - WinoGrande | 83.35 | Accuracy (%) (5-shot) | 88.4 |
| Open LLM Leaderboard v1 - HellaSwag | 87.81 | Normalized accuracy (%) (10-shot) | 88 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 68.67 | MC2 (%) (0-shot) | 87.9 |
| Open LLM Leaderboard v1 - MMLU | 66.27 | Accuracy (%) (5-shot) | 86.6 |
| Open LLM Leaderboard v1 - ARC Challenge | 69.11 | Normalized accuracy (%) (25-shot) | 82.2 |
| Open LLM Leaderboard v1 - GSM8K | 64.14 | Accuracy (%) (5-shot) | 77.8 |
Interactive version: theaggregate.ai/model?slug=burningbruce-solar-8x10-7b-bf16 · How It Works · Data refreshed daily, snapshot 2026-11-08.