Compare

Claude Haiku 4.5 vs GPT-5 Turbo

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

Verdict

GPT-5 Turbo leads on LMSYS ELO (1398 vs 1305). Claude Haiku 4.5 is ~6.6× cheaper on a 3:1 input:output blend.

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

OpenAI

OpenAI’s flagship unified model. Handles text, vision, and audio natively. The generalist benchmark champion.

Native multimodalStrong math and scienceHuge ecosystem

Pricing

Input / 1M$0.80$6.00

Output / 1M$4.00$24.00

Context200K400K

Max output16K32K

LicenseProprietaryProprietary

Released2025-10-012026-01-21

Benchmarks

LMSYS ELO1305.01398.0

MMLU Pro81.491.2

HumanEval87.093.0

SWE-Bench49.265.8

MATH76.891.5

GPQA—68.1

MMMU—78.8

IFEval87.388.9

Per-task cost

Summarize a 1-hour meeting transcript$0.014$0.102

Review a 500-line pull request$0.014$0.096

Answer a customer support ticket$0.0056$0.037

Extract structured data from a resume$0.0080$0.054

Debug a stack trace with context$0.013$0.084

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

Add up to four models, tweak tasks live.