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
$0.20$0.07
Cheapest input
$2.00Amazon Bedrock$0.70Mistral
Cheapest output
$10.00Amazon Bedrock$2.10Mistral
$900Anthropic list price$245Mistral list price
Benchmarks
BullshitBench v2
80%80%
Terminal-Bench 4.0
12.42%41%
BrowseComp
84.7%84.5%
AutomationBench
13.5%59.9%
AA-Briefcase v1.1
13591393
threejseval
12151008
Overview
CompanyAnthropicMistral
Release dateJun 30 2026Oct 6 2026
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Mistral Large 4 leads Claude Sonnet 5 on 3 of the 6 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. Claude Sonnet 5 shipped 98 days before Mistral Large 4, so benchmark comparisons should account for the intervening progress.

Context windows are 1M (Claude Sonnet 5) vs 1M (Mistral Large 4). Claude Sonnet 5 is closed, while Mistral Large 4 is open weight.

On BullshitBench v2, both models score 80%. On Terminal-Bench 4.0, Mistral Large 4 leads at 41% vs Claude Sonnet 5 at 12.42%. On BrowseComp, Claude Sonnet 5 leads at 84.7% vs Mistral Large 4 at 84.5%. On AutomationBench, Mistral Large 4 leads at 59.9% vs Claude Sonnet 5 at 13.5%. On AA-Briefcase v1.1, Mistral Large 4 leads at 1393 vs Claude Sonnet 5 at 1359. On threejseval, Claude Sonnet 5 leads at 1215 vs Mistral Large 4 at 1008.