Skip to content

mistral-small-2506

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±3.9 (95%): 53.3
benchmarksof 12: 11
per 1,000 documentsmean over its benchmarks: $0.39
seconds per inputmean response time: 86.7

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

By task

Data correction

28.9

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

44.5

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	96.2±2.0	–	$0.83$0.004 run	90.08	T0435 · 4 Jun 2026prompt.txt
Blacklist Cards	22.3±1.8	–	$0.094$0.003 run	1.31	T0442 · 25 Nov 2025prompt.txt
Book Advert XML Repair	10.6±6.4	–	$0.26$0.013 run	5.83	T0475 · 8 Dec 2025prompt.txt
Business Letters	59.0±6.8	–	$0.40$0.016 run	163.19	T0436 · 4 Jun 2026prompt.txt
Company Lists	90.7±7.8	–	$0.54$0.008 run	101.44	T0443 · 4 Jun 2026prompt.txt
Fraktur Adverts	32.5±28.2	–	$0.79$0.004 run	193.64	T0439 · 4 Jun 2026prompt_optimized.txt
General Meeting Minutes	83.9±10.2	–	$0.56$0.005 run	8.32	T1243 · 3 Jul 2026prompt.txt
Library Cards	83.6±2.5	–	$0.24$0.062 run	44.79	T0440 · 4 Jun 2026prompt.txt
Magazine Pages	6.6±5.1	–	$0.082$0.004 run	1.44	T0796 · 23 Mar 2026prompt.txt
Medieval Manuscripts	54.0±18.8	–	$0.34$0.003 run	119.09	T0441 · 4 Jun 2026prompt.txt
Personnel Cards	47.1±19.5	–	$0.19$0.011 run	224.67	T0603 · 4 Jun 2026prompt.txt

Not run on: Duty Rosters.

Price

From	Input, $ per million tokens	Output, $ per million tokens	Source
24 Nov 2025	0.1	0.3	archived price page

Every run