Prokaryote-8x7B-bf16: benchmark results
Kquant03's mixture-of-experts release whose published Mixtral configuration specifies 8 local experts, 2 selected per token and 32 decoder layers. Its recipe names alnrg2arg/test2_4 as the base; nominal expert sizes are not measured total or active parameter counts. Provider: Kquant03. Access: Open.
Aggregate Rating 1464 ± 41, rank #3104 of 10916 rated models, from 6 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard v1 - ARC Challenge | 73.72 | Normalized accuracy (%) (25-shot) | 98.2 |
| Open LLM Leaderboard v1 - HellaSwag | 88.18 | Normalized accuracy (%) (10-shot) | 90 |
| Open LLM Leaderboard v1 - GSM8K | 69.52 | Accuracy (%) (5-shot) | 89.5 |
| Open LLM Leaderboard v1 - WinoGrande | 83.03 | Accuracy (%) (5-shot) | 86.8 |
| Open LLM Leaderboard v1 - TruthfulQA MC2 | 67.79 | MC2 (%) (0-shot) | 86.5 |
| Open LLM Leaderboard v1 - MMLU | 64.97 | Accuracy (%) (5-shot) | 79.5 |
Interactive version: theaggregate.ai/model?slug=prokaryote-8x7b-bf16 · How It Works · Data refreshed daily, snapshot 2026-11-08.