Compare AI models

Specifications
Parameters
—1.05T
Context window
1M1M
API pricing
Input price
$4.00$0.70
Output price
$20.00$2.10
Cached input price
$0.20$0.07
Cheapest input
$4.00Amazon Bedrock$0.70Mistral
Cheapest output
$20.00Amazon Bedrock$2.10Mistral
$1,800Anthropic list price$245Mistral list price
Benchmarks
BullshitBench v2
63%80%
DeepSWE 1.1
74.2%61.7%
FrontierCode 2.0
45.5%19.7%
Terminal-Bench 4.0
66.4%41%
AutomationBench
40%59.9%
AA-Briefcase v1.1
18221393
threejseval
20651008
Overview
CompanyAnthropicMistral
Release dateSep 22 2026Oct 6 2026
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Claude Opus 5.5 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 $4.00 per million input tokens, and $2.10 vs $20.00 per million output tokens. Claude Opus 5.5 shipped 14 days before Mistral Large 4, so benchmark comparisons should account for the intervening progress.

Context windows are 1M (Claude Opus 5.5) vs 1M (Mistral Large 4). Claude Opus 5.5 is closed, while Mistral Large 4 is open weight.

On BullshitBench v2, Mistral Large 4 leads at 80% vs Claude Opus 5.5 at 63%. On DeepSWE 1.1, Claude Opus 5.5 leads at 74.2% vs Mistral Large 4 at 61.7%. On FrontierCode 2.0, Claude Opus 5.5 leads at 45.5% vs Mistral Large 4 at 19.7%. On Terminal-Bench 4.0, Claude Opus 5.5 leads at 66.4% vs Mistral Large 4 at 41%. On AutomationBench, Mistral Large 4 leads at 59.9% vs Claude Opus 5.5 at 40%. On AA-Briefcase v1.1, Claude Opus 5.5 leads at 1822 vs Mistral Large 4 at 1393. On threejseval, Claude Opus 5.5 leads at 2065 vs Mistral Large 4 at 1008.