modelgrep
N

Nous: Hermes 3 405B Instruct

nousresearch/hermes-3-llama-3.1-405b

133rd smartest of 178JSON
Use via OpenRouter ↗
Intelligence
17.6
133rd of 178
Design Elo
Speed
21
261st fastest
Latency
391ms
first token
Input price
$1.00
209th cheapest
Context
131K
16K max out

How it compares

Smarter than25%
of all ranked models
Faster than12%
of all ranked models
Cheaper than30%
of all ranked models

Overview

Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the...

Benchmarks

independent · via OpenRouter
Artificial Analysis26th percentile
Intelligence Index
17.6
Coding Index
18.1
Agentic Index
11.8
GPQA Diamond
54%
Humanity's Last Exam
4%
SciCode
35%
Tau²-Bench (agentic)
27%

Providers & pricing (1)

ProviderIn $/MOut $/MUptime
DeepInfrafp8$1.00$1.00100%

Specifications

Context window131K
Max output16K
Knowledge cutoffDec 2023
Input modalitiestext
Output modalitiestext
Prompt caching
Cache read price
ModeratedNo

Hermes 3 405B Instruct FAQ

How much does Hermes 3 405B Instruct cost?

Hermes 3 405B Instruct costs $1.00 per million input tokens and $1.00 per million output tokens via OpenRouter, making it 209th cheapest of 298 paid models.

How smart is Hermes 3 405B Instruct?

Hermes 3 405B Instruct scores 17.6 on the Artificial Analysis Intelligence Index, ranking 133rd of 178 benchmarked models, with a GPQA Diamond score of 54%.

How fast is Hermes 3 405B Instruct?

Hermes 3 405B Instruct generates around 21 tokens per second with 391ms time-to-first-token (p50), the 261st fastest tracked model.

What is Hermes 3 405B Instruct's context window?

Hermes 3 405B Instruct supports a 131K-token context window and can output up to 16K tokens. It accepts text input.

Compare head-to-head