Compare AI models

Specifications
Parameters
—1.05T
Context window
1M1M
API pricing
Input price
$5.00$0.70
Output price
$25.00$2.10
Cached input price
$0.50$0.07
Cheapest input
$5.00Amazon Bedrock$0.70Mistral
Cheapest output
$25.00Amazon Bedrock$2.10Mistral
$2,250Anthropic list price$245Mistral list price
Benchmarks
BullshitBench v2
95%80%
DeepSWE 1.1
59%61.7%
Terminal-Bench 4.0
23.64%41%
BrowseComp
84.3%84.5%
AutomationBench
15.5%59.9%
Overview
CompanyAnthropicMistral
Release dateMay 28 2026Oct 6 2026
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Mistral Large 4 leads Claude Opus 4.8 on 4 of the 5 benchmarks they both report. Mistral Large 4 is cheaper on both input and output: $0.70 vs $5.00 per million input tokens, and $2.10 vs $25.00 per million output tokens. Claude Opus 4.8 shipped 131 days before Mistral Large 4, so benchmark comparisons should account for the intervening progress.

Context windows are 1M (Claude Opus 4.8) vs 1M (Mistral Large 4). Claude Opus 4.8 is closed, while Mistral Large 4 is open weight.

On BullshitBench v2, Claude Opus 4.8 leads at 95% vs Mistral Large 4 at 80%. On DeepSWE 1.1, Mistral Large 4 leads at 61.7% vs Claude Opus 4.8 at 59%. On Terminal-Bench 4.0, Mistral Large 4 leads at 41% vs Claude Opus 4.8 at 23.64%. On BrowseComp, Mistral Large 4 leads at 84.5% vs Claude Opus 4.8 at 84.3%. On AutomationBench, Mistral Large 4 leads at 59.9% vs Claude Opus 4.8 at 15.5%.