readable AI benchmarks (simplified)

readable AI benchmarks

OpenAI

GPT-6 Astra (medium)

reasoning · closed weights · Sep 3, 2026

GPT-6 Astra (medium) has a Quality Score of 76.5, ranking 11th among 284 scored models. Per 1M tokens, pricing is $10.00 input, $50.00 output, $1.00 cached input, and $12.50 cached output. It accepts text and image input, outputs text, and has a 1M token context window. Its Reliability Score is 71.1, ranking 7th among 284 scored models, above average (total average: 35.4). Its Value Score is 42.7, high compared with the total Value average of 29.1.

Quality Score76.5coverage 94.7%: missing CursorBench 3.2 and DeepSWE v1.1
Value Score42.7
Reliability71.1
Cache Discount90%

Model specification

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

Token prices USD per 1M tokens

Input
$10.00
Output
$50.00
Cached Input
$1.00
Cached Output
$12.50
Cost per task
$0.747

Capability

Intelligence
59.2
Coding
76.7
Agentic
46.9
Omniscience
42.2
Correct
60.6%
Blended price
$7.70

Answer outcomes

Attempt rate: 78.9%

Correct 60.6%Incorrect 18.3%Abstained 21.1%

Artificial Analysis benchmarks

GDPval-AA v2
53%
τ³-Banking
35%
Terminal-Bench v2.1
90%
SciCode
51%
Humanity’s Last Exam
53%
GPQA Diamond
94%
CritPt
29%
AA-Omniscience
71%
AA-LCR
76%

Similar models