Skip to content

pixtral-large-2411

Mistral

legacy model Its test configurations are retired, so it is no longer run. The figures are from its best legacy runs, scored as they ran at the time; it is not ranked.

average: 53.5
benchmarksof 12: 10
per 1,000 documentsmean over its benchmarks: $8.58
seconds per inputmean response time: 93.0

Compare with other models Its row in the Matrix All its test runs

By task

Data correction

21.8

Best of 114 models with all its benchmarks: claude-opus-5-5, 82.7.
Transcription

53.7

Best of 114 models with all its benchmarks: gemini-4-argon, 96.2.

By benchmark

Benchmark	Score	Rank	Per 1,000 docs	s / input	Best run
Bibliographic Data	87.2±10.6	–	$16$0.080 run	114.27	T0035 · 4 Jun 2026prompt.txt
Blacklist Cardsolder run	77.8	–	$8.22$0.27 run	4.05	T0326 · 24 Oct 2025prompt.txt
Book Advert XML Repair	6.6±3.9	–	$5.79$0.29 run	89.95	T0469 · 24 Jan 2026prompt.txt
Business Letters	49.0±8.3	–	$7.56$0.30 run	146.46	T0023 · 4 Jun 2026prompt.txt
Company Lists	67.3±14.2	–	$11$0.17 run	115.32	T0381 · 4 Jun 2026prompt.txt
Fraktur Adverts	80.6±14.1	–	$16$0.081 run	61.25	T0095 · 4 Jun 2026prompt_optimized.txt
Library Cardsolder run	77.9	–	–– run	5.85	T0159 · 2 Sep 2025prompt.txt
Magazine Pages	7.9±5.7	–	$1.16$0.053 run	2.39	T0771 · 23 Mar 2026prompt.txt
Medieval Manuscripts	43.3±14.9	–	$7.42$0.089 run	175.3	T0294 · 4 Jun 2026prompt.txt
Personnel Cards	37.1±20.1	–	$3.54$0.22 run	215.18	T0604 · 4 Jun 2026prompt.txt

Not run on: Duty Rosters, General Meeting Minutes.

Price

From	Input, $ per million tokens	Output, $ per million tokens	Source
24 Nov 2025	2.0	6.0	archived price page

Every run