Skip to content

gemini-2.0-flash

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: 63.8
benchmarksof 12: 10
per 1,000 documentsmean over its benchmarks: $0.58
seconds per inputmean response time: 6.8

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

By task

Data correction

55.7

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

75.3

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 Dataolder run	84.8	–	$1.05$0.005 run	13.93	T0008 · 30 Sep 2025prompt.txt
Blacklist Cardsolder run	91.2	–	$0.37$0.012 run	4.4	T0313 · 24 Oct 2025prompt.txt
Book Advert XML Repair	18.9±7.2	–	$0.31$0.016 run	4.93	T0456 · 8 Dec 2025prompt.txt
Business Lettersolder run	54.0	–	$0.21$0.012 run	2.13	T0013 · 30 Sep 2025prompt.txt
Company Listsolder run	75.4	–	$0.63$0.010 run	9.41	T0355 · 28 Oct 2025prompt.txt
Fraktur Advertsolder run	72.6	–	$0.88$0.004 run	11.01	T0086 · 30 Sep 2025prompt_optimized.txt
Library Cardsolder run	85.2	–	–– run	2.33	T0151 · 24 Sep 2025prompt.txt
Magazine Pages	2.2±4.3	–	$0.71$0.033 run	9.1	T0768 · 23 Mar 2026prompt.txt
Medieval Manuscripts	60.7±16.1	–	$0.33$0.004 run	3.4	T0283 · 24 Jan 2026prompt.txt
Personnel Cards	92.5±2.1	–	$0.76$0.046 run	7.73	T0586 · 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