readable AI benchmarks (simplified)

readable AI benchmarks

OpenAI

GPT-6.2 Astra (Low)

reasoning · closed weights · Nov 17, 2026

GPT-6.2 Astra (Low) has a Quality Score of 57.5, ranking 43rd 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 69.3, ranking 39th among 288 scored models, above average (total average: 48.2). Its Value Score is 32.7, around average compared with the total Value average of 29.3.

Quality Score57.5coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score32.7
Factual reliability69.3
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
$0.662

Capability

Intelligence
45.7
Omniscience (native net)
38.7
Correct
60.6%
Blended price
$5.88

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 82.6%

Correct 60.6%Incorrect 22.0%Partial / not attempted 17.4%

Artificial Analysis benchmarks aa-v5

Current Intelligence Index components

AA-Briefcase v1.1
1038.7 Elo
AutomationBench-AA
68.6%
private 657-task split from dataset v1.0.6
GDP.pdf
28.0%
FrontierCode v2.0
32.7%
AA Stirrup · 132 tasks, 3 attempts per task
Terminal-Bench v4.0
51.0%
AA mini-swe-agent standardized runs · 66 tasks, pass@1 averaged over 3 repeats per task
AA-Omniscience v1.1
38.7 native net
HLE-Diamond
47.7%
CritPt v2 Hard
61.0%
AA Stirrup · hard subset, 40 of 70 problems
Terminal-Bench-Science v0.1.0
51.0%

Similar models

Support me! Patreon