readable AI benchmarks

Alibaba

Qwen3.7 Plus

reasoning · closed weights · Jun 1, 2026

Quality Score43.5
Value Score36.5
Reliability50.5
Cache Discount90%

Model specification

Reasoning
reasoning
Input modalities
text, image, video
Output modalities
text
Context window
1M tokens
Weights
closed weights

Token prices USD per 1M tokens

Input
$0.400
Output
$1.60
Cached Input
$0.040
Cached Output
$0.500
Cost per task
$0.242

Capability

Intelligence
39.4
Coding
55.9
Agentic
20.7
Omniscience
1.1
Correct
22.5%
Blended price
$0.268

Answer outcomes

Correct 22.5%Incorrect 21.4%Abstained 56.0%

Artificial Analysis benchmarks

GDPval-AA v2
22%
τ³-Banking
18%
Terminal-Bench v2.1
61%
SciCode
45%
Humanity’s Last Exam
36%
GPQA Diamond
90%
CritPt
9%
AA-Omniscience
51%
AA-LCR
69%

Similar models