Compare

GPT-5 Mini vs Claude Haiku 4.5

OpenAI vs Anthropic. Specs, benchmarks, and real per-task cost — all in one page.

Verdict

Claude Haiku 4.5 leads on LMSYS ELO (1305 vs 1288). GPT-5 Mini is ~1.8× cheaper on a 3:1 input:output blend.

OpenAI

GPT-5’s smaller, cheaper sibling. Optimized for chat and lightweight agent tasks.

Very low latencyCheap enough for mass consumer apps

Anthropic

Fast, cheap, and smart enough for most routing and extraction tasks. Great base model for subagents.

Sub-second latency10x cheaper than OpusStrong structured output

Pricing

Input / 1M$0.50$0.80

Output / 1M$2.00$4.00

Context256K200K

Max output16K16K

LicenseProprietaryProprietary

Released2026-01-212025-10-01

Benchmarks

LMSYS ELO1288.01305.0

MMLU Pro78.581.4

HumanEval85.587.0

SWE-Bench—49.2

MATH79.876.8

IFEval85.487.3

Per-task cost

Summarize a 1-hour meeting transcript$0.0085$0.014

Review a 500-line pull request$0.0080$0.014

Answer a customer support ticket$0.0031$0.0056

Extract structured data from a resume$0.0045$0.0080

Debug a stack trace with context$0.0070$0.013

Per-call cost using published token counts for each task. Real-world prompts vary.

Add up to four models, tweak tasks live.