Compare AI models

Specifications
Context window
1M1M
API pricing
Input price
$0.10$0.30
Output price
$0.50$2.50
Cached input price
$0.01$0.03
Cheapest input
$0.10Amazon Bedrock$0.15Google AI Studio
Cheapest output
$0.50Amazon Bedrock$1.25Google AI Studio
$45.00Anthropic list price$185Google list price
Benchmarks
BullshitBench v2
57%19%
Humanity's Last Exam · no tools
45.9%12.1%
Overview
CompanyAnthropicGoogle
Release dateOct 7 2026Apr 17 2025
AccessClosedClosed
Model detailsView modelView model

Frequently asked questions

Claude Haiku 5.5 leads Gemini 2.5 Flash on 2 of the 2 benchmarks they both report (BullshitBench v2, Humanity's Last Exam). Claude Haiku 5.5 is cheaper on both input and output: $0.10 vs $0.30 per million input tokens, and $0.50 vs $2.50 per million output tokens. Figures are base-tier rates. Gemini 2.5 Flash shipped 538 days before Claude Haiku 5.5, so benchmark comparisons should account for the intervening progress.

Context windows are 1M (Claude Haiku 5.5) vs 1M (Gemini 2.5 Flash).

On BullshitBench v2, Claude Haiku 5.5 leads at 57% vs Gemini 2.5 Flash at 19%. On Humanity's Last Exam · no tools, Claude Haiku 5.5 leads at 45.9% vs Gemini 2.5 Flash at 12.1%.