Compare AI models

Specifications
Parameters
—1.05T
Context window
1M1M
API pricing
Input price
$2.00$0.70
Output price
$10.00$2.10
Cached input price
$0.10$0.07
Cheapest input
$1.00Google AI Studio$0.70Mistral
Cheapest output
$5.00Google AI Studio$2.10Mistral
$900Google list price$245Mistral list price
Benchmarks
BullshitBench v2
66%80%
DeepSWE 1.1
77.9%61.7%
Terminal-Bench 4.0
57.4%41%
AutomationBench
51.3%59.9%
threejseval
17021008
Overview
CompanyGoogleMistral
Release dateSep 30 2026Oct 6 2026
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Gemini 4 Argon leads Mistral Large 4 on 3 of the 5 benchmarks they both report. Mistral Large 4 is cheaper on both input and output: $0.70 vs $2.00 per million input tokens, and $2.10 vs $10.00 per million output tokens. Gemini 4 Argon shipped 6 days before Mistral Large 4, so benchmark comparisons should account for the intervening progress.

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

On BullshitBench v2, Mistral Large 4 leads at 80% vs Gemini 4 Argon at 66%. On DeepSWE 1.1, Gemini 4 Argon leads at 77.9% vs Mistral Large 4 at 61.7%. On Terminal-Bench 4.0, Gemini 4 Argon leads at 57.4% vs Mistral Large 4 at 41%. On AutomationBench, Mistral Large 4 leads at 59.9% vs Gemini 4 Argon at 51.3%. On threejseval, Gemini 4 Argon leads at 1702 vs Mistral Large 4 at 1008.