Skip to main content

Claude Haiku 4.5 vs GPT-4.1

SpecClaude Haiku 4.5GPT-4.1
Respan Index19.2 (#130)19.2 (#130)
Blended price per 1M$2$3.5
Context window200K1.0M
Input / output per 1M$1 / $5$2 / $8
Max output64K33K
Inputtext, visiontext, vision
Released2025-10-152025-04-14

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 4.5GPT-4.1
Coding5.1 Claude Haiku 4.53.8 GPT-4.1
Agents15.6 Claude Haiku 4.511.8* GPT-4.1
Reasoning21.5 Claude Haiku 4.520.5 GPT-4.1
Knowledge & language13.2 Claude Haiku 4.530.9 GPT-4.1
Human preference49.1 Claude Haiku 4.547.3 GPT-4.1

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

Benchmarks both report

Claude Haiku 4.5 leads on 5 of the 8 benchmarks both report. Higher is better. Each score links to where it was published.

BenchmarkClaude Haiku 4.5GPT-4.1
LMArena Elo14141415
Chess Puzzles (Epoch AI)8%11%
GPQA Diamond71.2%66.3%
MATH Level 5 (Epoch AI)96.4%83%
OTIS Mock AIME 2024-2025 (Epoch AI)66.7%38.3%
SimpleQA Verified13.2%31.1%
WeirdML (Håvard Tveit Ihle)45.4%39%
SWE-bench Verified73.3%54.6%

FAQ

Is Claude Haiku 4.5 better than GPT-4.1?

Claude Haiku 4.5 and GPT-4.1 tie on the Respan Index at 19.2. Claude Haiku 4.5 leads on 5 of the 8 benchmarks both report.

Which is cheaper, Claude Haiku 4.5 or GPT-4.1?

Claude Haiku 4.5 lists at $1 input and $5 output per 1M tokens; GPT-4.1 at $2 and $8. Claude Haiku 4.5 is 1.8x cheaper per token at list price.

Which has the larger context window?

Claude Haiku 4.5 accepts 200K tokens and GPT-4.1 1.0M tokens.

Compare other models

vs

Built for AI agents.
Break less.
Ship more.