Skip to content

gemini-3.1-flash-lite-preview

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±4.3 (95%): 67.2
benchmarksof 12: 10
per 1,000 documentsmean over its benchmarks: $1.42
seconds per inputmean response time: 4.4

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

By task

Data correction

56.0

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

81.0

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	85.9±5.1	–	$3.19$0.016 run	7.99	T0669 · 16 Mar 2026prompt.txt
Blacklist Cards	95.9±2.8	–	$0.59$0.019 run	2.5	T0676 · 16 Mar 2026prompt.txt
Book Advert XML Repair	15.2±6.4	–	$0.91$0.045 run	3.02	T0679 · 16 Mar 2026prompt.txt
Business Letters	59.0±6.2	–	$0.68$0.039 run	2.77	T0670 · 16 Mar 2026prompt.txt
Company Lists	84.4±10.2	–	$2.03$0.030 run	5.15	T0677 · 16 Mar 2026prompt.txt
Fraktur Adverts	65.6±38.5	–	$2.85$0.014 run	6.7	T0673 · 16 Mar 2026prompt_optimized.txt
Library Cards	88.3±1.3	–	$0.66$0.17 run	2.36	T0674 · 16 Mar 2026prompt.txt
Magazine Pages	0.0±0.0	–	$0.45$0.021 run	2.37	T0812 · 23 Mar 2026prompt.txt
Medieval Manuscripts	80.7±12.4	–	$0.74$0.009 run	5.68	T0675 · 16 Mar 2026prompt.txt
Personnel Cards	96.7±1.3	–	$2.07$0.13 run	4.98	T0680 · 16 Mar 2026prompt.txt

Not run on: Duty Rosters, General Meeting Minutes.

Price

From	Input, $ per million tokens	Output, $ per million tokens	Source
16 Mar 2026	0.25	1.5	archived price page

Every run