Skip to content

qwen/qwen3.8-max

Qwenvia 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±3.3 (95%): 73.7
benchmarksof 12: 12
per 1,000 documentsmean over its benchmarks: $44
seconds per inputmean response time: 148.5

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

By task

Data correction

65.2

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

58.9

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

84.4

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

86.9

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	98.0±1.5	–	$68$0.34 run	215.82	T1465 · 4 Aug 2026prompt.txt
Blacklist Cards	95.7±2.4	–	$17$0.57 run	52.59	T1472 · 4 Aug 2026prompt.txt
Book Advert XML Repair	32.7±9.7	–	$59$2.96 run	199.66	T1475 · 4 Aug 2026prompt.txt
Business Letters	59.0±6.8	–	$21$1.17 run	68.25	T1466 · 4 Aug 2026prompt.txt
Company Lists	84.5±14.1	–	$31$0.46 run	122.39	T1473 · 4 Aug 2026prompt.txt
Duty Rosters	78.9±3.1	–	$89$1.88 run	308.33	T1479 · 4 Aug 2026prompt.txt
Fraktur Adverts	78.2±32.2	–	$64$0.32 run	244.82	T1469 · 4 Aug 2026prompt_optimized.txt
General Meeting Minutes	85.5±8.5	–	$45$0.41 run	142.19	T1478 · 4 Aug 2026prompt.txt
Library Cards	88.9±1.8	–	$23$5.94 run	128.05	T1470 · 4 Aug 2026prompt.txt
Magazine Pages	0.0±0.0	–	$17$0.78 run	44.24	T1477 · 4 Aug 2026prompt.txt
Medieval Manuscripts	84.9±11.4	–	$65$0.78 run	188.81	T1471 · 4 Aug 2026prompt.txt
Personnel Cards	97.7±0.9	–	$29$1.78 run	66.43	T1476 · 4 Aug 2026prompt.txt

Price

From	Input, $ per million tokens	Output, $ per million tokens	Source
4 Aug 2026	2.0	6.0	archived price page

Every run