Skip to content

gemini-2.5-flash-lite-preview-09-2025

Google

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: 56.5
benchmarksof 12: 10
per 1,000 documentsmean over its benchmarks: $2.14
seconds per inputmean response time: 9.7

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

By task

Data correction

47.0

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

73.4

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	75.1±12.2	–	$0.80$0.004 run	3.49	T0211 · 24 Jan 2026prompt.txt
Blacklist Cardsolder run	86.5	–	$0.12$0.004 run	0.91	T0318 · 24 Oct 2025prompt.txt
Book Advert XML Repair	6.5±4.1	–	$12$0.59 run	44.11	T0461 · 24 Jan 2026prompt.txt
Business Lettersolder run	50.0	–	$0.12$0.007 run	0.89	T0212 · 1 Oct 2025prompt.txt
Company Listsother promptolder run	59.7	–	$0.48$0.007 run	2.11	T0366 · 28 Oct 2025prompt_min.txt
Fraktur Adverts	60.7±34.9	–	$6.10$0.031 run	23.15	T0215 · 24 Jan 2026prompt_optimized.txt
Library Cardsolder run	66.8	–	$1.24$0.33 run	4.38	T0216 · 1 Oct 2025prompt.txt
Magazine Pages	0.0±0.0	–	$0.078$0.004 run	1.5	T0786 · 23 Mar 2026prompt.txt
Medieval Manuscripts	72.0±14.3	–	$0.17$0.002 run	14.38	T0286 · 31 Mar 2026prompt.txt
Personnel Cards	87.5±3.1	–	$0.55$0.034 run	2.46	T0590 · 9 Feb 2026prompt.txt

Not run on: Duty Rosters, General Meeting Minutes.

Price

From	Input, $ per million tokens	Output, $ per million tokens	Source
0 Sep 2025	0.1	0.4	archived price page

Every run