← All benchmarks

Hermes 4 - Llama-3.1 405B (Non-reasoning)

Nous Research · Released 2025-08-27 · Independent benchmark scores from Artificial Analysis

Intelligence Index
7.4
Output speed
42.7
tokens/sec
Blended price
$1.50
per 1M tokens
Time to first token
0.67s

Model metadata

Model IDd3968fd3-97d8-4693-8d26-19cefc6f5d5f
Slughermes-4-llama-3-1-405b
Release date2025-08-27
ProviderNous Research
Provider slugnous-research
Output speed42.7 tok/s
Time to first token0.67s
Time to first answer0.67s
Blended price ($/1M)$1.50
Input price ($/1M)$1.00
Output price ($/1M)$3.00

All evaluation scores (18)

aime—
aime 2515.3%
artificial analysis coding index—
artificial analysis intelligence index7.40
artificial analysis math index15.30
gpqa53.6%
hle4.2%
ifbench34.8%
lcr22.0%
livecodebench54.6%
math 500—
mmlu pro72.9%
scicode—
tau banking—
tau226.6%
terminalbench hard9.8%
terminalbench v2 1—
terminalbench v4 0—

Source: artificialanalysis.ai/models/hermes-4-llama-3-1-405b

Benchmark data from Artificial Analysis.