readable AI benchmarks (simplified)

readable AI benchmarks

OpenAI

GPT-6.2 Astra (Xhigh)

reasoning · closed weights · Nov 17, 2026

GPT-6.2 Astra (Xhigh) has a Quality Score of 67.8, ranking 9th among 283 scored models. Per 1M tokens, pricing is $8.00 input, $40.00 output, $0.400 cached input, and $10.00 cache write. It has a 1M token context window. Its Reliability Score is 74.1, ranking 12th among 288 scored models, above average (total average: 48.2). Its Value Score is 38.6, high compared with the total Value average of 29.3.

Quality Score67.8coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score38.6
Factual reliability74.1
Cache Discount95%

Model specification

Reasoning
reasoning
Input modalities
none
Output modalities
none
Context window
1M tokens
Weights
closed weights

Token prices USD per 1M tokens

Input
$8.00
Output
$40.00
Cached Input
$0.400
Cache write
$10.00
Cost per task
$2.52

Capability

Intelligence
61.6
Omniscience (native net)
48.3
Correct
67.2%
Blended price
$5.88

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 86.1%

Correct 67.2%Incorrect 18.9%Partial / not attempted 13.9%

Artificial Analysis benchmarks aa-v5

Current Intelligence Index components

AA-Briefcase v1.1
1594.4 Elo
AutomationBench-AA
76.1%
private 657-task split from dataset v1.0.6
GDP.pdf
28.0%
FrontierCode v2.0
49.0%
AA Stirrup · 132 tasks, 3 attempts per task
Terminal-Bench v4.0
64.1%
AA mini-swe-agent standardized runs · 66 tasks, pass@1 averaged over 3 repeats per task
AA-Omniscience v1.1
48.3 native net
HLE-Diamond
67.3%
CritPt v2 Hard
70.5%
AA Stirrup · hard subset, 40 of 70 problems
Terminal-Bench-Science v0.1.0
78.6%

Similar models

Support me! Patreon