Model Comparison

Claude 3.5 Haiku vs Hermes 3 70B

Claude 3.5 Haiku shows notably better performance in the majority of benchmarks. Hermes 3 70B is 2.6x cheaper per token.

Want to compare interactively?Try the playground

Performance Benchmarks

Comparative analysis across standard metrics

3 benchmarks

Claude 3.5 Haiku outperforms in 2 benchmarks (MATH, MMLU-Pro), while Hermes 3 70B is better at 1 benchmark (GPQA).

Claude 3.5 Haiku shows notably better performance in the majority of benchmarks.

Thu Apr 16 2026 • llm-stats.com

Arena Performance

Human preference votes

Pricing Analysis

Price comparison per million tokens

Hermes 3 70B costs less

For input processing, Claude 3.5 Haiku ($0.80/1M tokens) is 2.3x more expensive than Hermes 3 70B ($0.35/1M tokens).

For output processing, Claude 3.5 Haiku ($4.00/1M tokens) is 2.9x more expensive than Hermes 3 70B ($1.40/1M tokens).

In conclusion, Claude 3.5 Haiku is more expensive than Hermes 3 70B.*

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

Lowest available price from all providers
Thu Apr 16 2026 • llm-stats.com
Anthropic
Claude 3.5 Haiku
Input tokens$0.80
Output tokens$4.00
Best providerAWS Bedrock
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 3.5 Haiku accepts 200,000 input tokens compared to Hermes 3 70B's 131,072 tokens. Claude 3.5 Haiku can generate longer responses up to 200,000 tokens, while Hermes 3 70B is limited to 16,384 tokens.

Anthropic
Claude 3.5 Haiku
Input200,000 tokens
Output200,000 tokens
Nous Research
Hermes 3 70B
Input131,072 tokens
Output16,384 tokens
Thu Apr 16 2026 • llm-stats.com

License

Usage and distribution terms

Claude 3.5 Haiku 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 3.5 Haiku

Proprietary

Closed source

Hermes 3 70B

Apache 2.0

Open weights

Release Timeline

When each model was launched

Claude 3.5 Haiku was released on 2024-10-22, while Hermes 3 70B was released on 2024-08-15.

Claude 3.5 Haiku is 2 months newer than Hermes 3 70B.

Claude 3.5 Haiku

Oct 22, 2024

1.5 years ago

2mo newer
Hermes 3 70B

Aug 15, 2024

1.7 years ago

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 3.5 Haiku is available from Bedrock, Google, Anthropic. Hermes 3 70B is available from DeepInfra.

Claude 3.5 Haiku

bedrock logo
AWS Bedrock
Input Price:Input: $0.80/1MOutput Price:Output: $4.00/1M
google logo
Google
Input Price:Input: $0.80/1MOutput Price:Output: $4.00/1M
anthropic logo
Anthropic
Input Price:Input: $1.00/1MOutput Price:Output: $5.00/1M

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→

Key Takeaways

Anthropic
Larger context window (200,000 tokens)
Higher MATH score (69.4% vs 20.8%)
Higher MMLU-Pro score (65.0% vs 47.2%)
Nous Research
Less expensive input tokens
Less expensive output tokens
Has open weights
Higher GPQA score (66.1% vs 41.6%)

Detailed Comparison

AI Model Comparison Table
Feature
Anthropic
Claude 3.5 Haiku
Nous Research
Hermes 3 70B

FAQ

Common questions about Claude 3.5 Haiku vs Hermes 3 70B

Claude 3.5 Haiku shows notably better performance in the majority of benchmarks. Claude 3.5 Haiku 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.
Claude 3.5 Haiku scores HumanEval: 88.1%, MGSM: 85.6%, DROP: 83.1%, MATH: 69.4%, MMLU-Pro: 65.0%. Hermes 3 70B scores MT-Bench: 89.9%, HellaSwag: 88.2%, BoolQ: 88.0%, PIQA: 84.4%, Winogrande: 83.2%.
Hermes 3 70B is 2.3x cheaper for input tokens. Claude 3.5 Haiku costs $0.80/M input and $4.00/M output via bedrock. Hermes 3 70B costs $0.35/M input and $1.40/M output via deepinfra.
Claude 3.5 Haiku 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.
Key differences include context window (200K vs 131K), input pricing ($0.80 vs $0.35/M), licensing (Proprietary vs Apache 2.0). See the full comparison above for benchmark-by-benchmark results.
Claude 3.5 Haiku is developed by Anthropic and Hermes 3 70B is developed by Nous Research.