Skip to content

qwen3.5-flash-2026-02-23

Alibaba

average±5.1 (95%): 55.8
leaderboard rankof 114: 99
benchmarksof 12: 10
per 1,000 documentsmean over its benchmarks: $0.89
seconds per inputmean response time: 58.0

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.
Transcription

69.7

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	94.2±3.3	≈57of 115	$1.19$0.006 run	31.81	T0879 · 25 Mar 2026prompt.txt
Blacklist Cards	58.1±15.4	≈110of 114	$0.23$0.007 run	25.54	T0886 · 25 Mar 2026prompt.txt
Book Advert XML Repair	17.3±7.5	≈64of 119	$3.76$0.19 run	394.28	T0889 · 25 Mar 2026prompt.txt
Business Letters	56.0±6.4	≈75of 114	$0.53$0.030 run	16.63	T0880 · 25 Mar 2026prompt.txt
Company Lists	84.3±9.3	≈29of 114	$0.73$0.011 run	17.3	T0887 · 25 Mar 2026prompt.txt
Fraktur Adverts	52.9±42.6	≈67of 114	$0.98$0.005 run	29.29	T0883 · 25 Mar 2026prompt_optimized.txt
Library Cards	38.8±5.1	≈110of 114	$0.12$0.031 run	15.95	T0884 · 25 Mar 2026prompt.txt
Magazine Pages	0.0±0.0	≈79of 115	$0.18$0.008 run	19.24	T0891 · 25 Mar 2026prompt.txt
Medieval Manuscripts	70.7±15.4	≈27of 114	$0.42$0.005 run	8.57	T0885 · 25 Mar 2026prompt.txt
Personnel Cards	85.5±7.5	≈78of 114	$0.76$0.046 run	21.18	T0890 · 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	0.1	0.4	archived price page

Every run