Qwen 3.5 Plus

Release Date: 2/16/2026

Vals Index

Accuracy (Vals Index)

59.08% ± 2.00

Latency (Vals Index)

570.93s

Cost/Test (Vals Index)

$0.31

Context Window

991k

Max Output Tokens

66k

Input Modality

Hyperparameter settings
Default Provider : Alibaba

Temperature

0.6

Top P

Default

Top K

Default

Max Output Tokens

65,536

Show rankings only among open weight models

Benchmarks

Accuracy

Rankings

0.0%

± 2.00
16/ 39

0.0%

± 1.57
14/ 27

0.0%

± 1.13
22/ 46

0.0%

± 0.94
10/ 96

0.0%

± 2.89
13/ 44

0.0%

± 0.97
36/ 68

0.0%

± 3.15
39/ 48

0.0%

± 3.18
17/ 24

0.0%

± 1.11
32/ 95

0.0%

± 1.67
10/ 98

0.0%

± 1.00
11/ 102

0.0%

± 0.41
8/ 116

0.0%

± 0.19
13/ 95

0.0%

± 0.33
13/ 96

0.0%

± 1.01
65/ 65

0.0%

± 2.03
20/ 40

0.0%

± 5.25
19/ 51
Contact us
Or send us an email at contact@vals.ai
Proprietary Benchmarks (contact us to get access)
Academic Benchmarks

Read about our methodology.