The AI arena is free today

Open Superagent

Claude 3 Sonnet vs Hermes 3 70B

Claude 3 Sonnet shows notably better performance in the majority of benchmarks. Hermes 3 70B is 9.8x cheaper per token.

Anthropic · Nous Research · Updated for 2026

Which is better?

Claude 3 Sonnet outperforms in 4 benchmarks (ARC-C, HellaSwag, MATH, MMLU-Pro), while Hermes 3 70B is better at 2 benchmarks (GPQA, MMLU). Claude 3 Sonnet shows notably better performance in the majority of benchmarks.

On price, Hermes 3 70B is roughly 9.8x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.

Claude 3 Sonnet also accepts a larger context window (200,000 input tokens), making it the stronger choice for long documents and large codebases.

Based on current benchmark, pricing, and model metadata for 2026.

Choose Claude 3 Sonnet

  • you want the strongest raw capability — it leads on 4 of 6 shared benchmarks
  • you process long inputs — it offers a 200,000 token context window

Choose Hermes 3 70B

  • cost matters — it's about 9.8x cheaper per token
  • you want the most recent training data — it shipped Aug 2024
  • you need open weights you can self-host or fine-tune

At a glance

The differences that matter most.

Benchmark wins
4 of 6
2 of 6
Input price
$3.00 / M
$0.35 / M
Output price
$15.00 / M
$1.40 / M
Context window
200,000
131,072
Released
Feb 2024
Aug 2024
License
Proprietary
Apache 2.0

Performance Benchmarks

Comparative analysis across standard metrics

6 benchmarks

Claude 3 Sonnet outperforms in 4 benchmarks (ARC-C, HellaSwag, MATH, MMLU-Pro), while Hermes 3 70B is better at 2 benchmarks (GPQA, MMLU).

Claude 3 Sonnet shows notably better performance in the majority of benchmarks.

Mon Aug 24 2026 • llm-stats.com

Arena Performance

Playground indexes and blind preference scores

Pricing Analysis

Price comparison per million tokens

Hermes 3 70B costs less

For input processing, Claude 3 Sonnet ($3.00/1M tokens) is 8.6x more expensive than Hermes 3 70B ($0.35/1M tokens).

For output processing, Claude 3 Sonnet ($15.00/1M tokens) is 10.7x more expensive than Hermes 3 70B ($1.40/1M tokens).

In conclusion, Claude 3 Sonnet is more expensive than Hermes 3 70B.*

* Using a 3:1 ratio of input to output tokens

Lowest available price from all providers
Mon Aug 24 2026 • llm-stats.com
Anthropic
Claude 3 Sonnet
Input tokens$3.00
Output tokens$15.00
Best providerAnthropic
Nous Research
Hermes 3 70B
Input tokens$0.35
Output tokens$1.40
Best providerDeepinfra
Notice missing or incorrect data?Start an Issue

Context Window

Maximum input and output token capacity

Claude 3 Sonnet accepts 200,000 input tokens compared to Hermes 3 70B's 131,072 tokens. Claude 3 Sonnet can generate longer responses up to 200,000 tokens, while Hermes 3 70B is limited to 16,384 tokens.

Anthropic
Claude 3 Sonnet
Input200,000 tokens
Output200,000 tokens
Nous Research
Hermes 3 70B
Input131,072 tokens
Output16,384 tokens
Mon Aug 24 2026 • llm-stats.com

Input Capabilities

Supported data types and modalities

Claude 3 Sonnet supports multimodal inputs, whereas Hermes 3 70B does not.

Claude 3 Sonnet can handle both text and other forms of data like images, making it suitable for multimodal applications.

Claude 3 Sonnet

Text
Images
Audio
Video

Hermes 3 70B

Text
Images
Audio
Video

License

Usage and distribution terms

Claude 3 Sonnet is licensed under a proprietary license, while Hermes 3 70B uses Apache 2.0.

License differences may affect how you can use these models in commercial or open-source projects.

Claude 3 Sonnet

Proprietary

Closed source

Hermes 3 70B

Apache 2.0

Open weights

Release Timeline

When each model was launched

Claude 3 Sonnet was released on 2024-02-29, while Hermes 3 70B was released on 2024-08-15.

Hermes 3 70B is 6 months newer than Claude 3 Sonnet.

Claude 3 Sonnet

Feb 29, 2024

2.5 years ago

Hermes 3 70B

Aug 15, 2024

2.0 years ago

5mo newer

Knowledge Cutoff

When training data ends

Neither model specifies a knowledge cutoff date.

Unable to compare the recency of their training data.

No cutoff dates available

Provider Availability

Claude 3 Sonnet is available from Anthropic, Bedrock, Google. Hermes 3 70B is available from DeepInfra.

Claude 3 Sonnet

anthropic logo
Anthropic
Input Price:Input: $3.00/1MOutput Price:Output: $15.00/1M
bedrock logo
AWS Bedrock
Input Price:Input: $3.00/1MOutput Price:Output: $15.00/1M
google logo
Google
Input Price:Input: $3.00/1MOutput Price:Output: $15.00/1M

Hermes 3 70B

deepinfra logo
Deepinfra
Input Price:Input: $0.35/1MOutput Price:Output: $1.40/1M
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion

Judge for yourself.

Run your own prompts against Claude 3 Sonnet and Hermes 3 70B side-by-side, then vote on the output you prefer.

Claude 3 Sonnet
✓ Preferred
Hermes 3 70B
Open in Playground

FAQ

Common questions about Claude 3 Sonnet vs Hermes 3 70B.

Which is better, Claude 3 Sonnet or Hermes 3 70B?

Claude 3 Sonnet shows notably better performance in the majority of benchmarks. Claude 3 Sonnet is made by Anthropic and Hermes 3 70B is made by Nous Research. The best choice depends on your use case — compare their benchmark scores, pricing, and capabilities above.

How does Claude 3 Sonnet compare to Hermes 3 70B in benchmarks?

Claude 3 Sonnet scores ARC-C: 93.2%, GSM8k: 92.3%, HellaSwag: 89.0%, MGSM: 83.5%, BIG-Bench Hard: 82.9%. Hermes 3 70B scores MT-Bench: 89.9%, HellaSwag: 88.2%, BoolQ: 88.0%, PIQA: 84.4%, Winogrande: 83.2%.

Is Claude 3 Sonnet cheaper than Hermes 3 70B?

Hermes 3 70B is 8.6x cheaper for input tokens. Claude 3 Sonnet costs $3.00/M input and $15.00/M output via anthropic. Hermes 3 70B costs $0.35/M input and $1.40/M output via deepinfra.

What are the context window sizes for Claude 3 Sonnet and Hermes 3 70B?

Claude 3 Sonnet supports 200K tokens and Hermes 3 70B supports 131K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between Claude 3 Sonnet and Hermes 3 70B?

Key differences include context window (200K vs 131K), input pricing ($3.00 vs $0.35/M), multimodal support (yes vs no), licensing (Proprietary vs Apache 2.0). See the full comparison above for benchmark-by-benchmark results.

Who makes Claude 3 Sonnet and Hermes 3 70B?

Claude 3 Sonnet is developed by Anthropic and Hermes 3 70B is developed by Nous Research.