claude-3-opus-20240229

Anthropic

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: 38.9
benchmarksof 12: 8
per 1,000 documentsmean over its benchmarks: $82
seconds per inputmean response time: 24.7

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

By benchmark

Benchmark	Score	Rank	Per 1,000 docs	s / input	Best run
Bibliographic Dataolder run	40.4	–	$137$0.68 run	47.52	T0138 · 1 Oct 2025prompt.txt
Blacklist Cardsolder run	64.8	–	$44$1.45 run	7.84	T0321 · 24 Oct 2025prompt.txt
Book Advert XML Repair	16.9±6.9	–	$70$3.49 run	23.97	T0464 · 8 Dec 2025prompt.txt
Business Lettersolder run	26.0	–	$47$2.69 run	5.34	T0036 · 30 Sep 2025prompt.txt
Company Listsolder run	29.3	–	$131$1.96 run	47.01	T0371 · 28 Oct 2025prompt.txt
Fraktur Advertsolder run	19.1	–	$126$0.63 run	42.93	T0094 · 30 Sep 2025prompt_optimized.txt
Library Cardsolder run	75.5	–	$52$14 run	10.61	T0145 · 1 Oct 2025prompt.txt
Medieval Manuscriptsolder run	38.9	–	$54$0.65 run	12.65	T0289 · 24 Oct 2025prompt.txt

Not run on: Duty Rosters, General Meeting Minutes, Magazine Pages, Personnel Cards.

Price

From	Input, $ per million tokens	Output, $ per million tokens	Source
0 Sep 2025	15.0	75.0	archived price page

claude-3-opus-20240229

By benchmark

Price

Every run