Skip to content

magistral-medium-2509

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±5.0 (95%): 45.7
benchmarksof 12: 11
per 1,000 documentsmean over its benchmarks: $6.33
seconds per inputmean response time: 17.0

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

By task

Data correction

23.1

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

49.1

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	79.3±12.7	–	$11$0.057 run	29.46	T0425 · 4 Jun 2026prompt.txt
Blacklist Cards	51.9±14.8	–	$3.79$0.12 run	9.03	T0432 · 4 Jun 2026prompt.txt
Book Advert XML Repair	6.9±4.6	–	$4.69$0.23 run	17.61	T0474 · 8 Dec 2025prompt.txt
Business Letters	55.0±7.3	–	$9.42$0.47 run	10.43	T0426 · 4 Jun 2026prompt.txt
Company Listsother prompt	59.6±14.8	–	$8.11$0.12 run	23.72	T0434 · 4 Jun 2026prompt_min.txt
Fraktur Adverts	42.4±36.7	–	$10$0.052 run	37.38	T0429 · 4 Jun 2026prompt_optimized.txt
General Meeting Minutes	79.5±9.0	–	$9.02$0.081 run	20.26	T1235 · 3 Jul 2026prompt.txt
Library Cards	15.3±3.8	–	$0.90$0.24 run	7.41	T0430 · 4 Jun 2026prompt.txt
Magazine Pages	7.6±7.4	–	$2.57$0.12 run	8.45	T0795 · 4 Jun 2026prompt.txt
Medieval Manuscripts	65.5±19.4	–	$6.71$0.054 run	9.39	T0431 · 4 Jun 2026prompt.txt
Personnel Cards	39.4±20.9	–	$2.51$0.15 run	13.84	T0595 · 4 Jun 2026prompt.txt

Not run on: Duty Rosters.

Price

From	Input, $ per million tokens	Output, $ per million tokens	Source
24 Nov 2025	2.0	5.0	archived price page

Every run