Skip to main content

Claude Haiku 4.5 vs GPT-5 mini

SpecClaude Haiku 4.5GPT-5 mini
Respan Index19.3 (#131)20.0 (#129)
Blended price per 1M$2$0.688
Context window200K400K
Input / output per 1M$1 / $5$0.25 / $2
Max output64K128K
Inputtext, visiontext, vision
Released2025-10-152025-08-07

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-5 mini
Coding5.1 Claude Haiku 4.59.1 GPT-5 mini
Agents15.8 Claude Haiku 4.54.4 GPT-5 mini
Reasoning21.5 Claude Haiku 4.531.5 GPT-5 mini
Knowledge & language13.2 Claude Haiku 4.521.6 GPT-5 mini
Human preference49.1 Claude Haiku 4.543.9 GPT-5 mini

How the Respan Index works

Benchmarks both report

GPT-5 mini leads on 7 of the 10 benchmarks both report. Higher is better. Each score links to where it was published.

BenchmarkClaude Haiku 4.5GPT-5 mini
LMArena Elo14141390
Chess Puzzles (Epoch AI)8%24%
GPQA Diamond71.2%81.6%
MATH Level 5 (Epoch AI)96.4%97.8%
OTIS Mock AIME 2024-2025 (Epoch AI)66.7%86.7%
SAGE (Vals AI)31.8%43%
SimpleQA Verified13.2%21.6%
Vending-Bench 2 (Andon Labs)458.89-31.18
WeirdML (Håvard Tveit Ihle)45.4%52.7%
SWE-bench Verified73.3%71%

FAQ

Is Claude Haiku 4.5 better than GPT-5 mini?

GPT-5 mini scores 20.0 on the Respan Index (#129), ahead of Claude Haiku 4.5 at 19.3 (#131). GPT-5 mini leads on 7 of the 10 benchmarks both report.

Which is cheaper, Claude Haiku 4.5 or GPT-5 mini?

Claude Haiku 4.5 lists at $1 input and $5 output per 1M tokens; GPT-5 mini at $0.25 and $2. GPT-5 mini is 2.9x cheaper per token at list price.

Which has the larger context window?

Claude Haiku 4.5 accepts 200K tokens and GPT-5 mini 400K tokens.

Compare other models

vs

Built for AI agents.
Break less.
Ship more.