readable AI benchmarks

Alibaba

Qwen3.6 27B (Reasoning)

reasoning · open weights · Apr 22, 2026

Quality Score36.1
Value Score29.4
Reliability40.0
Cache Discountnot available

Model specification

Reasoning
reasoning
Input modalities
text, image, video
Output modalities
text
Context window
262,144 tokens
Weights
open weights

Token prices USD per 1M tokens

Input
$0.600
Output
$3.60
Cached Input
not available
Cached Output
not available
Cost per task
$0.292

Capability

Intelligence
37.7
Coding
53.7
Agentic
27.5
Omniscience
-20.0
Correct
19.6%
Blended price
$0.900

Answer outcomes

Correct 19.6%Incorrect 39.6%Abstained 40.8%

Artificial Analysis benchmarks

GDPval-AA v2
32%
τ³-Banking
17%
Terminal-Bench v2.1
61%
SciCode
40%
Humanity’s Last Exam
23%
GPQA Diamond
84%
CritPt
1%
AA-Omniscience
40%
AA-LCR
73%

Similar models