Compare AI models

Specifications
Parameters
—1.05T
Context window
1M1M
API pricing
Input price
$0.75$0.70
Output price
$3.75$2.10
Cached input price
$0.075$0.07
Cheapest input
$0.375Google AI Studio$0.70Mistral
Cheapest output
$1.875Google AI Studio$2.10Mistral
$338Google list price$245Mistral list price
Benchmarks
BullshitBench v2
39%80%
DeepSWE 1.1
49%61.7%
AutomationBench
17%59.9%
threejseval
13401008
Overview
CompanyGoogleMistral
Release dateJul 21 2026Oct 6 2026
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Mistral Large 4 leads Gemini 3.6 Flash on 3 of the 4 benchmarks they both report (BullshitBench v2, DeepSWE 1.1, AutomationBench, threejseval). Mistral Large 4 is cheaper on both input and output: $0.70 vs $0.75 per million input tokens, and $2.10 vs $3.75 per million output tokens. Gemini 3.6 Flash shipped 77 days before Mistral Large 4, so benchmark comparisons should account for the intervening progress.

Context windows are 1M (Gemini 3.6 Flash) vs 1M (Mistral Large 4). Gemini 3.6 Flash is closed, while Mistral Large 4 is open weight.

On BullshitBench v2, Mistral Large 4 leads at 80% vs Gemini 3.6 Flash at 39%. On DeepSWE 1.1, Mistral Large 4 leads at 61.7% vs Gemini 3.6 Flash at 49%. On AutomationBench, Mistral Large 4 leads at 59.9% vs Gemini 3.6 Flash at 17%. On threejseval, Gemini 3.6 Flash leads at 1340 vs Mistral Large 4 at 1008.