Mistral-Nemo-Instruct-2407-abliterated: benchmark results
Uncensored community variant of Mistral NeMo Instruct 2407 with refusal directions removed via abliteration. Provider: Mistral. Released 2024-08-15. Access: Open.
Unified ELO 1558 ± 1, rank #411 of 1392 rated models, from 11 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open Korean LLM Leaderboard | 48.42 | Average Score (%) | 96 |
| Open LLM Leaderboard - IFEval | 63.92 | Score | 76.3 |
| UGI - Writing | 38.9 | Writing Score | 68.9 |
| Open LLM Leaderboard - MATH Level 5 | 13.22 | Score | 58.3 |
| UGI - Natural Intelligence | 23.7 | NatInt Score | 56.8 |
| Open LLM Leaderboard - MMLU-Pro | 27.98 | Score | 52.1 |
| Open LLM Leaderboard - BBH | 29.92 | Score | 51.4 |
| Open LLM Leaderboard - MuSR | 10.15 | Score | 50.6 |
| UGI - Willingness (W/10) | 5.8 | W/10 Score | 49.8 |
| Open LLM Leaderboard - GPQA | 4.92 | Score | 41.8 |
| UGI Leaderboard | 31.12 | UGI Score | 35.1 |
Interactive version: theaggregate.ai/model?slug=mistral-nemo-instruct-2407-abliterated · How It Works · Data refreshed daily, snapshot 2026-09-05.