readable AI benchmarks (simplified)

readable AI benchmarks

OpenAI

GPT-6.2 Astra (Medium)

reasoning · closed weights · Nov 17, 2026

GPT-6.2 Astra (Medium) has a Quality Score of 64.7, ranking 15th 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 72.4, ranking 18th among 288 scored models, above average (total average: 48.2). Its Value Score is 36.8, high compared with the total Value average of 29.3.

Quality Score64.7coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score36.8
Factual reliability72.4
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
$1.62

Capability

Intelligence
57.0
Omniscience (native net)
44.8
Correct
64.2%
Blended price
$5.88

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 83.6%

Correct 64.2%Incorrect 19.4%Partial / not attempted 16.4%

Artificial Analysis benchmarks aa-v5

Current Intelligence Index components

AA-Briefcase v1.1
1408.2 Elo
AutomationBench-AA
72.8%
private 657-task split from dataset v1.0.6
GDP.pdf
28.4%
FrontierCode v2.0
46.6%
AA Stirrup · 132 tasks, 3 attempts per task
Terminal-Bench v4.0
58.6%
AA mini-swe-agent standardized runs · 66 tasks, pass@1 averaged over 3 repeats per task
AA-Omniscience v1.1
44.8 native net
HLE-Diamond
56.0%
CritPt v2 Hard
67.5%
AA Stirrup · hard subset, 40 of 70 problems
Terminal-Bench-Science v0.1.0
74.8%

Similar models

Support me! Patreon