readable AI benchmarks (simplified)

readable AI benchmarks

Alibaba

Qwen3 Max Thinking (Preview)

reasoning · closed weights · Nov 3, 2025

Qwen3 Max Thinking (Preview) has a Quality Score of 27.8, ranking 278th among 553 scored models. Per 1M tokens, pricing is $1.20 input, $6.00 output, and $0.240 cached input. It has a 262,144 token context window. Its Reliability Score is 30.4, ranking 303rd among 555 scored models, below average (total average: 35.7). Its Value Score is 19.4, low compared with the total Value average of 30.7.

Quality Score27.8coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score19.4
Factual reliability30.4
Cache Discount80%

Model specification

Reasoning
reasoning
Input modalities
none
Output modalities
none
Context window
262,144 tokens
Weights
closed weights

Token prices USD per 1M tokens

Input
$1.20
Output
$6.00
Cached Input
$0.240
Cache write
not available
Cost per task
not available

Capability

Intelligence
16.3
Coding
not available
Agentic
not available
Omniscience
-39.1
Correct
27.4%
Blended price
$1.01

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 93.8%

Correct 27.4%Incorrect 66.5%Partial / not attempted 6.2%

Artificial Analysis benchmarks

Humanity’s Last Exam
13%
GPQA Diamond
78%
CritPt
0%
AA-Omniscience
30%
AA-LCR
62%

Similar models

Support me! Patreon