Skip to content

mistral-medium-2505

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: 61.2
benchmarksof 12: 11
per 1,000 documentsmean over its benchmarks: $2.32
seconds per inputmean response time: 114.8

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

By task

Data correction

40.9

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

63.1

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	96.0±1.9	–	$4.76$0.024 run	165.31	T0170 · 4 Jun 2026prompt.txt
Blacklist Cardsolder run	87.8	–	$0.93$0.031 run	5.39	T0328 · 24 Oct 2025prompt.txt
Book Advert XML Repair	6.2±3.5	–	$1.67$0.083 run	23.37	T0471 · 24 Jan 2026prompt.txt
Business Letters	58.0±10.6	–	$1.39$0.029 run	167.78	T0172 · 4 Jun 2026prompt.txt
Company Lists	67.5±13.4	–	$2.91$0.044 run	62.75	T0385 · 4 Jun 2026prompt.txt
Fraktur Adverts	50.6±41.0	–	$3.71$0.019 run	270.75	T0178 · 4 Jun 2026prompt_optimized.txt
General Meeting Minutes	76.9±10.7	–	$2.92$0.026 run	33.75	T1240 · 3 Jul 2026prompt.txt
Library Cardsolder run	77.6	–	–– run	3.55	T0180 · 26 Sep 2025prompt.txt
Magazine Pages	14.3±8.8	–	$0.94$0.043 run	185.69	T0782 · 4 Jun 2026prompt.txt
Medieval Manuscripts	63.2±16.4	–	$1.59$0.018 run	145.94	T0296 · 4 Jun 2026prompt.txt
Personnel Cards	75.5±9.6	–	$2.40$0.15 run	198.39	T0601 · 4 Jun 2026prompt.txt

Not run on: Duty Rosters.

Price

From	Input, $ per million tokens	Output, $ per million tokens	Source
0 Sep 2025	0.4	2.0	archived price page

Every run