readable AI benchmarks

Alibaba

Qwen3.6 27B (Non-reasoning)

non-reasoning · open weights · Apr 22, 2026

Quality Score26.2
Value Score24.1
Reliability23.4
Cache Discountnot available

Model specification

Reasoning
non-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
$0.398

Capability

Intelligence
31.3
Coding
46.6
Agentic
23.6
Omniscience
-53.2
Correct
16.7%
Blended price
$0.900

Answer outcomes

Correct 16.7%Incorrect 69.9%Abstained 13.4%

Artificial Analysis benchmarks

GDPval-AA v2
31%
τ³-Banking
9%
Terminal-Bench v2.1
51%
SciCode
37%
Humanity’s Last Exam
15%
GPQA Diamond
83%
CritPt
1%
AA-Omniscience
23%
AA-LCR
64%

Similar models