Hermes 4 - Llama-3.1 70B
Reasoning
Creator
Nous Research
Released
2025-08-27
Intelligence
16.0
Artificial Analysis Index
Coding
14.4
Artificial Analysis Index
In $/1M
$0.13
input tokens
Out $/1M
$0.40
output tokens
Blended $/1M
$0.20
3:1 blended
Speed
91
tokens / sec
Benchmark breakdown
Independent evaluation scores, normalized to 0–100.
GPQA Diamond
70
Humanity’s Last Exam
8
MMLU-Pro
81
SciCode
34
LiveCodeBench
65
MATH-500—
AIME 2025
69
τ²-Bench (agentic)
23
Terminal-Bench Hard
5
IFBench
31