Compare AI models

Specifications
Parameters
—1.05T
Context window
1M1M
API pricing
Input price
$0.10$0.70
Output price
$0.50$2.10
Cached input price
$0.01$0.07
Cheapest input
$0.10Amazon Bedrock$0.70Mistral
Cheapest output
$0.50Amazon Bedrock$2.10Mistral
$45.00Anthropic list price$245Mistral list price
Benchmarks
BullshitBench v2
57%80%
Terminal-Bench 4.0
39.2%41%
AA-Briefcase v1.1
15781393
threejseval
14241008
Overview
CompanyAnthropicMistral
Release dateOct 7 2026Oct 6 2026
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Claude Haiku 5.5 and Mistral Large 4 are evenly matched across the 4 benchmarks they both report (BullshitBench v2, Terminal-Bench 4.0, AA-Briefcase v1.1, threejseval). Claude Haiku 5.5 is cheaper on both input and output: $0.10 vs $0.70 per million input tokens, and $0.50 vs $2.10 per million output tokens. Figures are base-tier rates. Mistral Large 4 shipped 1 day before Claude Haiku 5.5, so benchmark comparisons should account for the intervening progress.

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

On BullshitBench v2, Mistral Large 4 leads at 80% vs Claude Haiku 5.5 at 57%. On Terminal-Bench 4.0, Mistral Large 4 leads at 41% vs Claude Haiku 5.5 at 39.2%. On AA-Briefcase v1.1, Claude Haiku 5.5 leads at 1578 vs Mistral Large 4 at 1393. On threejseval, Claude Haiku 5.5 leads at 1424 vs Mistral Large 4 at 1008.