MMODELYST
Models/Hermes 3 - Llama-3.1 70B
MDL

Hermes 3 - Llama-3.1 70B

Nous Research

Verified against Artificial Analysis · Jul 13, 2026
Capability
47
percentile index
Price /M
$0.7 / $0.7
in / out
Context
131.1K
tokens
Avg score
32.8
6 benchmarks
AA Intelligence
5.1
index
Speed
36 tok/s
TTFT 0.3s
Released
Aug 15, 2024
About

Hermes 3 - Llama-3.1 70B is a open-weights model in the Hermes family from Nous Research. Benchmarked on 6 evals, averaging 32.8.

Benchmark scores · 6
avg 32.8 — higher is better
MMLU-Pro
57.1
MATH
53.8
GPQA Diamond
40.1
SciCode
23.1
LiveCodeBench
18.8
Humanity's Last Exam
4.1
The research behind this model
all papers mentioning it →

Mentions matched by name in title/abstract — from the arXiv + HF daily corpus.

Details
PublisherNous Research
FamilyHermes
Parameters
License
WeightsOpen
ReleasedAug 15, 2024
Performance & price
Output speed36 tok/s
Latency (TTFT)0.3s
Price in / out$0.7 / $0.7 per 1M
Blended price$0.7 / 1M

Median across API providers, via Artificial Analysis. Blended = 3:1 input:output. For reasoning models, latency includes thinking time. Methodology →

Capability over time

Append-only ledger — every observed change to this model's numbers.

API providers
Artificial Analysis$0.7/M