Hermes-4-14B — benchmark results

Nous Research's open 14B Hermes 4 (September 2025), a Qwen3-14B-based hybrid reasoner with tool calling and deliberately neutral alignment. Provider: Nous Research. Released 2025-08-26. Access: Open.

Unified ELO 1527 ± 10, rank #695 of 1776 rated models, from 58 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
LatamBoard - ASSIN2 RTE94.36Score (%)100
LatamBoard - BLUEX74.27Score (%)100
LatamBoard - ENEM Challenge83.07Score (%)100
LatamBoard - FLORES Bidirectional47.41Score (%)100
LatamBoard - FaQuAD NLI82.81Score (%)100
LatamBoard - OAB Exams61.82Score (%)100
LatamBoard - Portuguese Score90.81Score (%)100
LatamBoard - Spanish PAWS66.35Score (%)100
LatamBoard - Spanish Score67.28Score (%)100
LatamBoard - Translation Score48.25Score (%)100
LatamBoard - Spanish TeleIA76.19Score (%)98.5
LatamBoard - Spanish XNLI49.44Score (%)93.9

Interactive version: theaggregate.ai/model?slug=hermes-4-14b · How the rankings work · Data refreshed daily, snapshot 2026-07-22.