Captain-Eris_Violet-V0.420-12B: benchmark results
Nitral-AI's SLERP merge of its Captain_BMO tune with Violet Twilight, two roleplay-leaning Mistral Nemo 12B models. Provider: Other. Released 2024-12-16. Access: Open.
Unified ELO 1512 ± 1, rank #642 of 1392 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - MuSR | 13.9 | Score | 76.4 |
| Open LLM Leaderboard - BBH | 35.33 | Score | 71.3 |
| Open LLM Leaderboard - GPQA | 8.17 | Score | 68.6 |
| Open LLM Leaderboard - MMLU-Pro | 30.25 | Score | 61.1 |
| UGI - Willingness (W/10) | 5.8 | W/10 Score | 49.8 |
| Open LLM Leaderboard - MATH Level 5 | 10.73 | Score | 49.5 |
| Open LLM Leaderboard - IFEval | 43.39 | Score | 45.8 |
| UGI Leaderboard | 31.45 | UGI Score | 36.8 |
| UGI - Writing | 28.9 | Writing Score | 33.1 |
| UGI - Natural Intelligence | 18.14 | NatInt Score | 32.8 |
Interactive version: theaggregate.ai/model?slug=captain-eris-violet-v0-420-12b · How It Works · Data refreshed daily, snapshot 2026-09-05.