Mistral Nemo Instruct (2407) — benchmark results
July 2024 Mistral Nemo Instruct checkpoint. Provider: Mistral. Released 2024-07-18. Access: Open.
Unified ELO 1465 ± 10, rank #929 of 1776 rated models, from 201 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| BTZSC - LLM | 66.97 | Macro-F1 (%) | 100 |
| BTZSC - Topic | 69.05 | Macro-F1 (%) | 100 |
| HumanLikeness - Meaning-2 | 75.1 | Humanlike Score (%) | 100 |
| BTZSC | 66.97 | Macro-F1 (%) | 97.1 |
| EuroEval Portuguese NLU - MultiWikiQA PT | 76.99 | Reading comprehension Score (%) | 92.2 |
| EuroEval Italian NLU - SQuAD IT | 73.31 | Reading comprehension Score (%) | 89.2 |
| EuroEval French NLU - FQuAD | 73 | Reading comprehension Score (%) | 87.9 |
| Open Japanese LLM - Wiki PAS SET F1 | 8.98 | Score (%) | 85.8 |
| Open Japanese LLM - Xlsum JA RougeLsum | 25.82 | Score (%) | 84.4 |
| HumanLikeness - Discourse-2 | 67.84 | Humanlike Score (%) | 84.2 |
| HumanLikeness - Overall | 63.97 | Overall Humanlike (%) | 84.2 |
| HumanLikeness - Sound-1 | 74.09 | Humanlike Score (%) | 84.2 |
Interactive version: theaggregate.ai/model?slug=mistral-nemo-instruct-2407 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.