Compare AI models

Specifications
Context window
200k1M
Benchmarks
BullshitBench v2
10%20%
Overview
CompanyAnthropicGoogle
Release dateMar 4 2024May 19 2026
AccessClosedClosed
Model detailsView modelView model

Frequently asked questions

Gemini 3.5 Flash leads Claude 3 Haiku on 1 of the 1 benchmark they both report (BullshitBench v2). Claude 3 Haiku shipped 806 days before Gemini 3.5 Flash, so benchmark comparisons should account for the intervening progress.

Context windows are 200k (Claude 3 Haiku) vs 1M (Gemini 3.5 Flash).

On BullshitBench v2, Gemini 3.5 Flash leads at 20% vs Claude 3 Haiku at 10%.