Skip to main content

Claude Haiku 4.5 vs DeepSeek V3.1

SpecClaude Haiku 4.5DeepSeek V3.1
Respan Index19.3 (#131)18.9 (#136)
Blended price per 1M$2$0.425
Context window200K128K
Input / output per 1M$1 / $5$0.25 / $0.95
Max output64K-
Inputtext, visiontext
Released2025-10-152025-08-21

Respan Index by category

Each category is scored 0 to 100, and how far ahead the winner is. Leads under a point are close to even.

CategoryClaude Haiku 4.5DeepSeek V3.1
Coding5.1 Claude Haiku 4.54.6 DeepSeek V3.1
Agents15.8 Claude Haiku 4.510.9 DeepSeek V3.1
Reasoning21.5 Claude Haiku 4.525.6 DeepSeek V3.1
Knowledge & language13.2 Claude Haiku 4.514.5* DeepSeek V3.1
Human preference49.1 Claude Haiku 4.547.9 DeepSeek V3.1

* Estimated: no published scores in that category. How the Respan Index works

Benchmarks both report

They split the 2 benchmarks both report evenly. Higher is better. Each score links to where it was published.

BenchmarkClaude Haiku 4.5DeepSeek V3.1
LMArena Elo14141417
WeirdML (Håvard Tveit Ihle)45.4%38.4%

FAQ

Is Claude Haiku 4.5 better than DeepSeek V3.1?

Claude Haiku 4.5 scores 19.3 on the Respan Index (#131), ahead of DeepSeek V3.1 at 18.9 (#136). They split the 2 benchmarks both report evenly.

Which is cheaper, Claude Haiku 4.5 or DeepSeek V3.1?

Claude Haiku 4.5 lists at $1 input and $5 output per 1M tokens; DeepSeek V3.1 at $0.25 and $0.95. DeepSeek V3.1 is 4.7x cheaper per token at list price.

Which has the larger context window?

Claude Haiku 4.5 accepts 200K tokens and DeepSeek V3.1 128K tokens.

Compare other models

vs

Built for AI agents.
Break less.
Ship more.