x-ai/grok-4

xAIvia OpenRouter

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: 38.1
benchmarksof 12: 8
per 1,000 documentsmean over its benchmarks: $133
seconds per inputmean response time: 194.7

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

By task

Data correction

49.6

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

31.5

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	55.5±1.9	–	$317$1.58 run	390.76	T0265 · 25 Jan 2026prompt.txt
Blacklist Cards	91.0±3.0	–	$33$1.10 run	39.1	T0336 · 25 Jan 2026prompt.txt
Book Advert XML Repair	43.2±10.3	–	$141$7.06 run	197.28	T0481 · 25 Jan 2026prompt.txt
Business Letters	10.0±6.2	–	$58$3.29 run	67.39	T0266 · 25 Jan 2026prompt.txt
Company Listsolder run	10.3	–	$118$1.77 run	353.47	T0401 · 28 Oct 2025prompt.txt
Fraktur Adverts	1.2±2.3	–	$174$0.87 run	221.08	T0269 · 25 Jan 2026prompt_optimized.txt
Medieval Manuscripts	37.4±13.7	–	$152$1.82 run	202.93	T0304 · 25 Jan 2026prompt.txt
Personnel Cards	56.0±5.5	–	$75$4.57 run	85.19	T0620 · 9 Feb 2026prompt.txt

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

Price

From	Input, $ per million tokens	Output, $ per million tokens	Source
20 Oct 2025	3.0	15.0	archived price page

x-ai/grok-4

By task

Data correction

Transcription

By benchmark

Price

Every run