Skip to content

qwen3.5-122b-a10b

Alibaba

average±2.1 (95%): 70.4
leaderboard rankof 114: ≈63
benchmarksof 12: 10
per 1,000 documentsmean over its benchmarks: $6.07
seconds per inputmean response time: 33.0

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

By task

Data correction

58.2

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

89.3

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	93.9±4.0	≈57of 115	$7.88$0.039 run	38.68	T0853 · 25 Mar 2026prompt.txt
Blacklist Cards	92.0±3.6	≈51of 114	$1.68$0.055 run	8.18	T0860 · 25 Mar 2026prompt.txt
Book Advert XML Repair	18.6±6.4	≈64of 119	$29$1.43 run	180.3	T0863 · 25 Mar 2026prompt.txt
Business Letters	57.0±6.6	≈65of 114	$2.22$0.13 run	9.09	T0854 · 25 Mar 2026prompt.txt
Company Lists	88.9±8.0	≈6of 114	$4.56$0.068 run	21.4	T0861 · 25 Mar 2026prompt.txt
Fraktur Adverts	97.0±1.8	≈15of 114	$5.98$0.030 run	30.82	T0857 · 25 Mar 2026prompt_optimized.txt
Library Cards	85.5±1.7	≈51of 114	$1.30$0.34 run	5.81	T0858 · 25 Mar 2026prompt.txt
Magazine Pages	0.0±0.0	≈79of 115	$1.46$0.067 run	5.85	T0865 · 25 Mar 2026prompt.txt
Medieval Manuscripts	73.3±15.5	≈27of 114	$2.04$0.025 run	9.91	T0859 · 25 Mar 2026prompt.txt
Personnel Cards	97.7±1.0	≈1of 114	$4.95$0.30 run	19.78	T0864 · 25 Mar 2026prompt.txt

Not run on: Duty Rosters, General Meeting Minutes.

Price

From	Input, $ per million tokens	Output, $ per million tokens	Source
24 Mar 2026	0.4	3.2	archived price page

Every run