Price Per TokenPrice Per Token
Nousresearch
Nousresearch
vs
Nousresearch
Nousresearch

Hermes 2 Pro - Llama-3 8B vs Hermes 4 70B

A detailed comparison of pricing, benchmarks, and capabilities

OpenClaw

Best LLMs for OpenClaw Vote for which model works best with OpenClaw

100 out of our 304 tracked models have had a price change in February.

Get our weekly newsletter on pricing changes, new releases, and tools.

Key Takeaways

Hermes 2 Pro - Llama-3 8B wins:

  • Cheaper output tokens
  • Higher intelligence benchmark

Hermes 4 70B wins:

  • Cheaper input tokens
  • Larger context window
  • Faster response time
  • Better at coding
  • Better at math
Price Advantage
Hermes 2 Pro - Llama-3 8B
Benchmark Advantage
Hermes 4 70B
Context Window
Hermes 4 70B
Speed
Hermes 4 70B

Pricing Comparison

Price Comparison

MetricHermes 2 Pro - Llama-3 8BHermes 4 70BWinner
Input (per 1M tokens)$0.14$0.11 Hermes 4 70B
Output (per 1M tokens)$0.14$0.38 Hermes 2 Pro - Llama-3 8B
Using a 3:1 input/output ratio, Hermes 2 Pro - Llama-3 8B is 21% cheaper overall.

Hermes 2 Pro - Llama-3 8B Providers

Novita $0.14 (Cheapest)

Hermes 4 70B Providers

Chutes $0.11 (Cheapest)
Nebius $0.13

Benchmark Comparison

7
Benchmarks Compared
1
Hermes 2 Pro - Llama-3 8B Wins
2
Hermes 4 70B Wins

Benchmark Scores

BenchmarkHermes 2 Pro - Llama-3 8BHermes 4 70BWinner
Intelligence Index
Overall intelligence score
22.113.6
Coding Index
Code generation & understanding
-9.2-
Math Index
Mathematical reasoning
-11.3-
MMLU Pro
Academic knowledge
22.866.4
GPQA
Graduate-level science
5.749.1
LiveCodeBench
Competitive programming
-26.9-
BBH
Big-Bench Hard
30.7--
Hermes 4 70B significantly outperforms in coding benchmarks.

Cost vs Quality

X-axis:
Y-axis:
Loading chart...
Hermes 2 Pro - Llama-3 8B
Other models

Context & Performance

Context Window

Hermes 2 Pro - Llama-3 8B
8,192
tokens
Max output: 8,192 tokens
Hermes 4 70B
131,072
tokens
Max output: 131,072 tokens
Hermes 4 70B has a 94% larger context window.

Speed Performance

MetricHermes 2 Pro - Llama-3 8BHermes 4 70BWinner
Tokens/secondN/A73.3 tok/s
Time to First TokenN/A0.62s

Capabilities

Feature Comparison

FeatureHermes 2 Pro - Llama-3 8BHermes 4 70B
Vision (Image Input)
Tool/Function Calls
Reasoning Mode
Audio Input
Audio Output
PDF Input
Prompt Caching
Web Search

License & Release

PropertyHermes 2 Pro - Llama-3 8BHermes 4 70B
LicenseOpen SourceOpen Source
AuthorNousresearchNousresearch
ReleasedMay 2024Aug 2025

Hermes 2 Pro - Llama-3 8B Modalities

Input
text
Output
text

Hermes 4 70B Modalities

Input
text
Output
text

Related Comparisons

Compare Hermes 2 Pro - Llama-3 8B with:

Compare Hermes 4 70B with:

Frequently Asked Questions

Hermes 4 70B has cheaper input pricing at $0.11/M tokens. Hermes 2 Pro - Llama-3 8B has cheaper output pricing at $0.14/M tokens.
Hermes 4 70B scores higher on coding benchmarks with a score of 9.2, compared to Hermes 2 Pro - Llama-3 8B's score of N/A.
Hermes 2 Pro - Llama-3 8B has a 8,192 token context window, while Hermes 4 70B has a 131,072 token context window.
Hermes 2 Pro - Llama-3 8B does not support vision. Hermes 4 70B does not support vision.