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
73%80%
DeepSWE 1.1
68.8%61.7%
Terminal-Bench 4.0
51.82%41%
BrowseComp
90.8%84.5%
AutomationBench
26.9%59.9%
AA-Briefcase v1.1
16731393
threejseval
17131008
Overview
CompanyAnthropicMistral
Release dateJul 24 2026Oct 6 2026
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Claude Opus 5 leads Mistral Large 4 on 5 of the 7 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 5 shipped 74 days before Mistral Large 4, so benchmark comparisons should account for the intervening progress.

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

On BullshitBench v2, Mistral Large 4 leads at 80% vs Claude Opus 5 at 73%. On DeepSWE 1.1, Claude Opus 5 leads at 68.8% vs Mistral Large 4 at 61.7%. On Terminal-Bench 4.0, Claude Opus 5 leads at 51.82% vs Mistral Large 4 at 41%. On BrowseComp, Claude Opus 5 leads at 90.8% vs Mistral Large 4 at 84.5%. On AutomationBench, Mistral Large 4 leads at 59.9% vs Claude Opus 5 at 26.9%. On AA-Briefcase v1.1, Claude Opus 5 leads at 1673 vs Mistral Large 4 at 1393. On threejseval, Claude Opus 5 leads at 1713 vs Mistral Large 4 at 1008.