Nous-Hermes-2-Mixtral-8x7B-SFT — benchmark results
Nous Research's SFT-only Hermes 2 fine-tune of Mixtral 8x7B, released as the sibling to the flagship SFT+DPO variant for comparison. Provider: Nous Research. Released 2023-12-26. Access: Open.
Unified ELO 1418 ± 46, rank #1141 of 1776 rated models, from 7 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - IFEval | 57.31 | Score | 69.2 |
| BiGGen-Bench | 3.6 | Average Score (1-5) | 67.6 |
| Open LLM Leaderboard - GPQA | 6.94 | Score | 58.2 |
| Open LLM Leaderboard - MuSR | 11.14 | Score | 57.6 |
| Open LLM Leaderboard - BBH | 30.59 | Score | 53.9 |
| Open LLM Leaderboard - MMLU-Pro | 22.96 | Score | 38.8 |
| Open LLM Leaderboard - MATH Level 5 | 2.11 | Score | 14.7 |
Interactive version: theaggregate.ai/model?slug=nous-hermes-2-mixtral-8x7b-sft · How the rankings work · Data refreshed daily, snapshot 2026-07-22.