mini-magnum-12B-v1.1: benchmark results
intervitens' 12B magnum-series fine-tune of Mistral Nemo Base 2407, designed to replicate the prose quality of Claude 3 Sonnet and Opus. Provider: Other. Released 2024-07-24. Access: Open.
Unified ELO 1503 ± 1, rank #679 of 1392 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - IFEval | 51.56 | Score | 61.5 |
| UGI - Writing | 34.26 | Writing Score | 51.9 |
| Open LLM Leaderboard - BBH | 29.73 | Score | 50.6 |
| Open LLM Leaderboard - MMLU-Pro | 25.46 | Score | 45.8 |
| Open LLM Leaderboard - GPQA | 5.15 | Score | 43.2 |
| Open LLM Leaderboard - MuSR | 8.09 | Score | 37.9 |
| Open LLM Leaderboard - MATH Level 5 | 6.19 | Score | 33.9 |
| UGI - Willingness (W/10) | 3.8 | W/10 Score | 28.3 |
| UGI - Natural Intelligence | 16.02 | NatInt Score | 23.6 |
| UGI Leaderboard | 26.67 | UGI Score | 22.3 |
Interactive version: theaggregate.ai/model?slug=mini-magnum-12b-v1-1 · How It Works · Data refreshed daily, snapshot 2026-09-05.