Compare

Claude Haiku 4.5 vs Gemini 2.5 Flash

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

Verdict

Gemini 2.5 Flash leads on LMSYS ELO (1312 vs 1305). Gemini 2.5 Flash is ~3.0× 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

Google DeepMind

Google’s price/performance darling. 1M context at $0.30/M input — nobody comes close on throughput-per-dollar.

Absurd cost-to-context ratioFast multimodalFree tier via AI Studio

Pricing

Input / 1M$0.80$0.30

Output / 1M$4.00$1.20

Context200K1.0M

Max output16K32K

LicenseProprietaryProprietary

Released2025-10-012026-02-05

Benchmarks

LMSYS ELO1305.01312.0

MMLU Pro81.482.1

HumanEval87.085.8

SWE-Bench49.2—

MATH76.884.2

MMMU—74.6

IFEval87.386.1

Per-task cost

Summarize a 1-hour meeting transcript$0.014$0.0051

Review a 500-line pull request$0.014$0.0048

Answer a customer support ticket$0.0056$0.0019

Extract structured data from a resume$0.0080$0.0027

Debug a stack trace with context$0.013$0.0042

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

Add up to four models, tweak tasks live.