Aspire-8B-model_stock: benchmark results
DreadPoor's model-stock merge of five Llama 3.1 8B fine-tunes, mixing uncensored, roleplay, and SuperNova/Hermes ingredients. Provider: DreadPoor. Released 2024-09-16. Access: Open.
Aggregate Rating 1491 ± 45, rank #2496 of 10916 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - IFEval | 71.41 | Score | 84.9 |
| Open LLM Leaderboard - GPQA | 31.46 | Score | 71.3 |
| UGI - Willingness (W/10) | 6.8 | W/10 Score | 67.6 |
| Open LLM Leaderboard - BBH | 52.78 | Score | 63.3 |
| Open LLM Leaderboard - MMLU-Pro | 37.63 | Score | 63.1 |
| Open LLM Leaderboard - MuSR | 42.12 | Score | 62 |
| Open LLM Leaderboard - MATH Level 5 | 14.95 | Score | 61.8 |
| UGI Leaderboard | 35.91 | UGI Score | 53.3 |
| UGI - Writing | 27.04 | Writing Score | 27.1 |
| UGI - Natural Intelligence | 15.64 | NatInt Score | 21 |
Interactive version: theaggregate.ai/model?slug=aspire-8b-model-stock · How It Works · Data refreshed daily, snapshot 2026-11-08.