readable AI benchmarks (simplified)

readable AI benchmarks

Thinking Machines

Inkling (Xhigh)

reasoning · open weights · Jul 15, 2026

Inkling (Xhigh) has a Quality Score of 44.7, ranking 152nd among 571 scored models. Per 1M tokens, pricing is $1.00 input, $4.05 output, and $0.170 cached input. It accepts text, image, and audio input, outputs text, and has a 1M token context window. Its Reliability Score is 51.0, ranking 115th among 573 scored models, above average (total average: 36.5). Its Value Score is 32.5, around average compared with the total Value average of 31.4.

Quality Score44.7coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score32.5
Factual reliability51.0
Cache Discount83%

Model specification

Reasoning
reasoning
Input modalities
text, image, audio
Output modalities
text
Context window
1M tokens
Weights
open weights

Token prices USD per 1M tokens

Input
$1.00
Output
$4.05
Cached Input
$0.170
Cache write
not available
Cost per task
not available

Capability

Intelligence
25.0
Coding
not available
Agentic
not available
Omniscience
2.0
Correct
41.5%
Blended price
$0.724

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 81.1%

Correct 41.5%Incorrect 39.5%Partial / not attempted 18.9%

Artificial Analysis benchmarks

GDPval-AA v2
29%
τ³-Banking
29%
SciCode
47%
Humanity’s Last Exam
32%
GPQA Diamond
87%
CritPt
5%
AA-Omniscience
51%
AA-LCR
77%

Similar models

Support me! Patreon