DeepSeek-V3 vs Claude 3.5 Haiku Comparison

Comparing DeepSeek-V3 and Claude 3.5 Haiku across benchmarks, pricing, and capabilities.

Want to compare interactively?Try the playground

Performance Benchmarks

Comparative analysis across standard metrics

4 benchmarks

DeepSeek-V3 outperforms in 4 benchmarks (DROP, GPQA, MMLU-Pro, SWE-Bench Verified), while Claude 3.5 Haiku is better at 0 benchmarks.

DeepSeek-V3 significantly outperforms across most benchmarks.

Thu Mar 19 2026 • llm-stats.com

Arena Performance

Human preference votes

Pricing Analysis

Price comparison per million tokens

DeepSeek-V3 costs less

For input processing, DeepSeek-V3 ($0.27/1M tokens) is 3.0x cheaper than Claude 3.5 Haiku ($0.80/1M tokens).

For output processing, DeepSeek-V3 ($1.10/1M tokens) is 3.6x cheaper than Claude 3.5 Haiku ($4.00/1M tokens).

In conclusion, Claude 3.5 Haiku is more expensive than DeepSeek-V3.*

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

Lowest available price from all providers

Thu Mar 19 2026 • llm-stats.com

DeepSeek-V3

Input tokens$0.27

Output tokens$1.10

Best providerDeepSeek

Claude 3.5 Haiku

Input tokens$0.80

Output tokens$4.00

Best providerAWS Bedrock

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 DeepSeek-V3's 131,072 tokens. Claude 3.5 Haiku can generate longer responses up to 200,000 tokens, while DeepSeek-V3 is limited to 131,072 tokens.

DeepSeek-V3

Input131,072 tokens

Output131,072 tokens

Claude 3.5 Haiku

Input200,000 tokens

Output200,000 tokens

Thu Mar 19 2026 • llm-stats.com

License

Usage and distribution terms

DeepSeek-V3 is licensed under MIT + Model License (Commercial use allowed), while Claude 3.5 Haiku uses a proprietary license.

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

DeepSeek-V3

MIT + Model License (Commercial use allowed)

Open weights

Claude 3.5 Haiku

Proprietary

Closed source

Release Timeline

When each model was launched

DeepSeek-V3 was released on 2024-12-25, while Claude 3.5 Haiku was released on 2024-10-22.

DeepSeek-V3 is 2 months newer than Claude 3.5 Haiku.

DeepSeek-V3

Dec 25, 2024

1.2 years ago

2mo newer

Claude 3.5 Haiku

Oct 22, 2024

1.4 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

DeepSeek-V3 is available from DeepSeek. Claude 3.5 Haiku is available from Bedrock, Google, Anthropic. The availability of providers can affect quality of the model and reliability.