Skip to content

meta-llama/llama-4-maverick

Metavia OpenRouter

average: 62.7
leaderboard rankof 114: 88
benchmarksof 12: 12
per 1,000 documentsmean over its benchmarks: $1.10
seconds per inputmean response time: 46.1

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

By task

Data correction

51.4

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

55.9

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

75.9

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

69.1

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	83.6±12.9	≈74of 115	$2.45$0.012 run	35.52	T0234 · 24 Jan 2026prompt.txt
Blacklist Cardsolder run	82.8	≈95of 114	$0.40$0.013 run	2.71	T0333 · 24 Oct 2025prompt.txt
Book Advert XML Repair	11.5±5.4	≈89of 119	$0.47$0.024 run	35.51	T0478 · 18 Sep 2026prompt.txt
Business Letters	53.0±6.6	≈90of 114	$0.69$0.039 run	3.86	T0248 · 17 Feb 2026prompt.txt
Company Listsolder run	72.5	≈80of 114	$0.86$0.013 run	22.33	T0395 · 28 Oct 2025prompt.txt
Duty Rosters	74.1±2.9	≈64of 107	$2.10$0.044 run	27.86	T1304 · 18 Sep 2026prompt.txt
Fraktur Adverts	59.0±34.6	≈67of 114	$2.24$0.011 run	92.61	T0251 · 24 Jan 2026prompt_optimized.txt
General Meeting Minutes	80.7±10.3	≈25of 108	$0.90$0.008 run	24.34	T1257 · 3 Jul 2026prompt.txt
Library Cards	84.8±1.7	≈51of 114	$0.78$0.21 run	271.32	T0252 · 17 Sep 2026prompt.txt
Magazine Pages	2.2±4.3	≈79of 115	$0.46$0.021 run	3.71	T0789 · 23 Mar 2026prompt.txt
Medieval Manuscripts	56.9±16.1	≈72of 114	$0.68$0.008 run	10.52	T0301 · 18 Sep 2026prompt.txt
Personnel Cards	91.3±3.3	≈78of 114	$1.22$0.075 run	22.95	T0616 · 16 Sep 2026prompt.txt

Price

From	Input, $ per million tokens	Output, $ per million tokens	Source
16 Sep 2026	0.1875	0.6525	archived price page
22 Jul 2026	0.2	0.8	archived price page
17 Oct 2025	0.15	0.6	archived price page

Every run