readable AI benchmarks (simplified)

readable AI benchmarks

Alibaba

Qwen3.5 27B (Reasoning)

reasoning · open weights · Feb 24, 2026

Qwen3.5 27B (Reasoning) has a Quality Score of 31.6, ranking 240th among 551 scored models. Per 1M tokens, pricing is $0.300 input and $2.40 output. It accepts text, image, video, and audio input, outputs text, and has a 262,144 token context window. Its Reliability Score is 28.0, ranking 332nd among 553 scored models, below average (total average: 35.6).

Quality Score31.6coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Scorenot available
Factual reliability28.0
Cache Discountnot available

Model specification

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

Token prices USD per 1M tokens

Input
$0.300
Output
$2.40
Cached Input
not available
Cache write
not available
Cost per task
not available

Capability

Intelligence
22.9
Coding
not available
Agentic
not available
Omniscience
-44.0
Correct
20.7%
Blended price
not available

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 85.3%

Correct 20.7%Incorrect 64.7%Partial / not attempted 14.7%

Artificial Analysis benchmarks

Humanity’s Last Exam
24%
GPQA Diamond
86%
CritPt
1%
AA-Omniscience
28%
AA-LCR
78%

Similar models

Support me! Patreon