← All Models

Claude Haiku 4.5 vs DeepSeek V3.2

DeepSeek V3.2 leads in 3 of 8 categories

Arena ELO

DeepSeek V3.2

Cheaper

DeepSeek V3.2

Faster

Claude Haiku 4.5

Detailed Comparison

CategoryClaude Haiku 4.5DeepSeek V3.2
ProviderAnthropic DeepSeek
Context Window200K WIN128K
Input Price ($/1M)$0.8 $0.27 WIN
Output Price ($/1M)$4 $1.1 WIN
Arena ELO1290 1380 WIN
Codingunknown unknown
Reasoningunknown unknown
Speed (tokens/sec)~120 t/s WIN~80 t/s
Open SourceNo Yes

Frequently Asked Questions

Which is cheaper, Claude Haiku 4.5 or DeepSeek V3.2?

DeepSeek V3.2 is approximately 71% cheaper than Claude Haiku 4.5 per million tokens.

Which is better for coding, Claude Haiku 4.5 or DeepSeek V3.2?

Claude Haiku 4.5 scores unknown on coding benchmarks, while DeepSeek V3.2 scores unknown.

Which has a larger context window?

Claude Haiku 4.5 supports 200K context, while DeepSeek V3.2 supports 128K.

Is Claude Haiku 4.5 or DeepSeek V3.2 open source?

Claude Haiku 4.5 is proprietary. DeepSeek V3.2 is open source.

Which ranks higher on the Chatbot Arena leaderboard?

DeepSeek V3.2 ranks higher with ELO 1380 vs 1290.