Compare AI models

Specifications
Parameters
—109B
Context window
1M10M
API pricing
Cheapest input
—$0.08DeepInfra
Cheapest output
—$0.24DeepInfra
—$35.00DeepInfra · fp8
Benchmarks
BullshitBench v2
20%20%
Overview
CompanyGoogleMeta
Release dateMay 19 2026Apr 5 2025
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Gemini 3.5 Flash and LLaMA 4 Scout are evenly matched across the 1 benchmark they both report (BullshitBench v2). LLaMA 4 Scout shipped 409 days before Gemini 3.5 Flash, so benchmark comparisons should account for the intervening progress.

Context windows are 1M (Gemini 3.5 Flash) vs 10M (LLaMA 4 Scout). Gemini 3.5 Flash is closed, while LLaMA 4 Scout is open weight.

On BullshitBench v2, both models score 20%.