readable AI benchmarks (simplified)

readable AI benchmarks

OpenAI

GPT-6 Astra (max)

reasoning · closed weights · Sep 3, 2026

GPT-6 Astra (max) has a Quality Score of 78.5, ranking 5th 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 71.7, ranking 4th among 284 scored models, above average (total average: 35.4). Its Value Score is 44.2, high compared with the total Value average of 29.1.

Quality Score78.5coverage 94.7%: missing CursorBench 3.2 and DeepSWE v1.1
Value Score44.2
Reliability71.7
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
$1.67

Capability

Intelligence
61.2
Coding
76.9
Agentic
51.5
Omniscience
43.4
Correct
62.6%
Blended price
$7.70

Answer outcomes

Attempt rate: 81.8%

Correct 62.6%Incorrect 19.2%Abstained 18.2%

Artificial Analysis benchmarks

GDPval-AA v2
56%
τ³-Banking
41%
Terminal-Bench v2.1
88%
SciCode
54%
Humanity’s Last Exam
55%
GPQA Diamond
96%
CritPt
32%
AA-Omniscience
72%
AA-LCR
74%

Similar models