Skip to content

claude-opus-4-1-20250805

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: 65.8
benchmarksof 12: 12
per 1,000 documentsmean over its benchmarks: $102
seconds per inputmean response time: 22.5

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

By task

Data correction

57.0

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

54.8

Best of 107 models with all its benchmarks: gpt-6-astra, 97.0.
Information extraction

77.5

Best of 107 models with all its benchmarks: grok-4.6, 90.8.
Transcription

73.6

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	93.7	–	$195$0.97 run	40.66	T0127 · 30 Sep 2025prompt.txt
Blacklist Cards	92.1±2.9	–	$52$1.73 run	6.92	T0324 · 24 Jan 2026prompt.txt
Book Advert XML Repair	26.3±7.9	–	$72$3.60 run	14.0	T0467 · 24 Jan 2026prompt.txt
Business Letters	47.0±6.6	–	$62$3.56 run	4.77	T0117 · 24 Jan 2026prompt.txt
Company Lists	78.5±11.4	–	$117$1.75 run	23.13	T0377 · 24 Jan 2026prompt.txt
Duty Rosters	76.7±3.2	–	$178$3.74 run	53.96	T1277 · 24 Jul 2026prompt.txt
Fraktur Advertsolder run	59.2	–	–– run	55.43	T0123 · 13 Aug 2025prompt_optimized.txt
General Meeting Minutes	70.8±21.3	–	$116$1.05 run	27.17	T1211 · 3 Jul 2026prompt.txt
Library Cardsolder run	83.6	–	–– run	7.24	T0146 · 2 Sep 2025prompt.txt
Magazine Pages	0.0±0.0	–	$39$1.81 run	4.28	T0778 · 23 Mar 2026prompt.txt
Medieval Manuscripts	74.0±12.8	–	$62$0.74 run	15.56	T0292 · 24 Jan 2026prompt.txt
Personnel Cards	87.7±10.9	–	$130$7.94 run	17.45	T0577 · 9 Feb 2026prompt.txt

Price

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

Every run