Compare AI models

Specifications
Parameters
—1.05T
Context window
1M1M
API pricing
Input price
—$0.70
Output price
—$2.10
Cached input price
—$0.07
Cheapest input
—$0.70Mistral
Cheapest output
—$2.10Mistral
—$245Mistral list price
Benchmarks
BullshitBench v2
35%80%
DeepSWE 1.1
65.3%61.7%
Terminal-Bench 4.0
11.21%41%
AutomationBench
30.4%59.9%
threejseval
14681008
Overview
CompanyGoogleMistral
Release dateAug 13 2026Oct 6 2026
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Mistral Large 4 leads Gemini 3.7 Flash on 3 of the 5 benchmarks they both report. Only Mistral Large 4 has a verified first-party price for an available API: $0.70 per million input tokens and $2.10 per million output tokens. No currently available pay-as-you-go API rate is tracked for Gemini 3.7 Flash. Gemini 3.7 Flash shipped 54 days before Mistral Large 4, so benchmark comparisons should account for the intervening progress.

Context windows are 1M (Gemini 3.7 Flash) vs 1M (Mistral Large 4). Gemini 3.7 Flash is closed, while Mistral Large 4 is open weight.

On BullshitBench v2, Mistral Large 4 leads at 80% vs Gemini 3.7 Flash at 35%. On DeepSWE 1.1, Gemini 3.7 Flash leads at 65.3% vs Mistral Large 4 at 61.7%. On Terminal-Bench 4.0, Mistral Large 4 leads at 41% vs Gemini 3.7 Flash at 11.21%. On AutomationBench, Mistral Large 4 leads at 59.9% vs Gemini 3.7 Flash at 30.4%. On threejseval, Gemini 3.7 Flash leads at 1468 vs Mistral Large 4 at 1008.