readable AI benchmarks (simplified)

readable AI benchmarks

Alibaba

Qwen3.6 Max Preview

reasoning · closed weights · Apr 20, 2026

Qwen3.6 Max Preview has a Quality Score of 49.1, ranking 93rd among 551 scored models. Per 1M tokens, pricing is $1.30 input, $7.80 output, and $0.130 cached input. It accepts text input, outputs text, and has a 256k token context window. Its Reliability Score is 54.6, ranking 79th among 553 scored models, above average (total average: 35.6). Its Value Score is 33.9, around average compared with the total Value average of 30.7.

Quality Score49.1coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score33.9
Factual reliability54.6
Cache Discount90%

Model specification

Reasoning
reasoning
Input modalities
text
Output modalities
text
Context window
256k tokens
Weights
closed weights

Token prices USD per 1M tokens

Input
$1.30
Output
$7.80
Cached Input
$0.130
Cache write
not available
Cost per task
not available

Capability

Intelligence
28.4
Coding
not available
Agentic
not available
Omniscience
9.2
Correct
37.9%
Blended price
$1.13

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 66.6%

Correct 37.9%Incorrect 28.7%Partial / not attempted 33.4%

Artificial Analysis benchmarks

Humanity’s Last Exam
31%
GPQA Diamond
89%
CritPt
4%
AA-Omniscience
55%
AA-LCR
81%

Similar models

Support me! Patreon