L3-8B-Lunaris-v1: benchmark results
Sao10K's generalist-plus-roleplay TIES merge of five Llama 3 8B models, positioned as a more balanced successor to Stheno v3.2. Provider: Sao10K. Released 2024-06-26. Access: Open.
Aggregate Rating 1479 ± 47, rank #2669 of 10916 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - IFEval | 68.95 | Score | 81.9 |
| Open LLM Leaderboard - MMLU-Pro | 37.87 | Score | 64.7 |
| Open LLM Leaderboard - BBH | 52.35 | Score | 60.9 |
| Open LLM Leaderboard - GPQA | 30.12 | Score | 57.4 |
| UGI - Writing | 32.63 | Writing Score | 45.9 |
| Open LLM Leaderboard - MATH Level 5 | 9.06 | Score | 44.4 |
| UGI - Willingness (W/10) | 4 | W/10 Score | 31.5 |
| Open LLM Leaderboard - MuSR | 37.27 | Score | 25.3 |
| UGI - Natural Intelligence | 14.57 | NatInt Score | 16.4 |
| UGI Leaderboard | 21.63 | UGI Score | 14.2 |
Interactive version: theaggregate.ai/model?slug=l3-8b-lunaris-v1 · How It Works · Data refreshed daily, snapshot 2026-11-08.