Llama-3SOME-8B-v2 — benchmark results
TheDrummer's (BeaverAI) NSFW roleplay fine-tune of Llama 3 8B, the v2 of his 3SOME series tuned for adult creative writing. Provider: Meta. Released 2024-06-21. Access: Open.
Unified ELO 1438 ± 21, rank #1054 of 1776 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - MMLU-Pro | 30.59 | Score | 62.6 |
| Open LLM Leaderboard - BBH | 31.7 | Score | 58.2 |
| Open LLM Leaderboard - GPQA | 6.94 | Score | 58.2 |
| Open LLM Leaderboard - IFEval | 45.08 | Score | 49.6 |
| Open LLM Leaderboard - MATH Level 5 | 9.37 | Score | 45.3 |
| UGI - Writing | 29.48 | Writing Score | 35.3 |
| Open LLM Leaderboard - MuSR | 7.21 | Score | 33.8 |
| UGI - Willingness (W/10) | 3.8 | W/10 Score | 27.8 |
| UGI - Natural Intelligence | 14.31 | NatInt Score | 16.1 |
| UGI Leaderboard | 19.18 | UGI Score | 10.5 |
Interactive version: theaggregate.ai/model?slug=llama-3some-8b-v2 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.