Compare

GPT-5 Turbo vs Claude Haiku 4.5

OpenAI vs Anthropic. 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.

OpenAI

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

Native multimodalStrong math and scienceHuge ecosystem

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$6.00$0.80

Output / 1M$24.00$4.00

Context400K200K

Max output32K16K

LicenseProprietaryProprietary

Released2026-01-212025-10-01

Benchmarks

LMSYS ELO1398.01305.0

MMLU Pro91.281.4

HumanEval93.087.0

SWE-Bench65.849.2

MATH91.576.8

GPQA68.1—

MMMU78.8—

IFEval88.987.3

Per-task cost

Summarize a 1-hour meeting transcript$0.102$0.014

Review a 500-line pull request$0.096$0.014

Answer a customer support ticket$0.037$0.0056

Extract structured data from a resume$0.054$0.0080

Debug a stack trace with context$0.084$0.013

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

Add up to four models, tweak tasks live.