Navigate
AI BENCHY
Advertise here

GPT-6 Astra — high vs max

The average score is effectively tied at 9.9 vs 9.9. high has the lower benchmark cost at $3.474 vs $3.803. high is faster at 18.65s vs 61.27s, with pass rates of 97.0% vs 95.5%.

Last updated at: 2026-09-04

Rank
#4
Total Output Tokens
53,622
Response Time (avg)
18.65s
Total Cost
$3.474
Rank
#3
Total Output Tokens
60,230
Response Time (avg)
61.27s
Total Cost
$3.803
Recommended model high

It has the best score here (9.9), while responding about 3.3x faster than GPT-6 Astra (max).

Detailed comparison

Metric GPT-6 Astra GPT-6 Astra high Release: 2026-09-04 GPT-6 Astra GPT-6 Astra max Release: 2026-09-04
Score 9.9 9.9
Rank #4 #3
Reliability 9.9 9.5
Consistency 9.6 10.0
Attempts 66/66 66/66
Tests Correct
Attempt pass rate 97.0% 95.5%
Flaky tests 1 0
Total Runs 66 66
Cost per result 16.543 18.106
Total Cost $3.474 $3.803
Input Price $10.000 / 1M $10.000 / 1M
Output Price $50.000 / 1M $50.000 / 1M
Total Input Tokens 79,290 79,058
Output Tokens 4,847 4,853
Reasoning Tokens 48,775 55,377
Response Time (avg) 18.65s 61.27s
Response Time (max) 254.93s 960.01s
Response Time (total) 410.28s 1347.96s
Parameters ~2T total (~150B active) ~2T total (~150B active)
Availability Closed Closed

Model generation showcase

Hamster playing table tennis

Prompt: Create a detailed SVG illustration of a hamster playing table tennis.

#4 GPT-6 Astra

high
Cost
$0.457
Time
176.7s
Tokens
9,218 tok

#3 GPT-6 Astra

max
No output was saved. The original provider response or failure reason is unavailable.
Cost
$0.000
Time
600.0s
Tokens
0 tok

Top Models by Score

Score vs Total Cost

Response Time (avg)

Score vs Response Time (avg)

Total Output Tokens

Score vs Total Output Tokens

Category Breakdown

Coding Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
GPT-6 Astra 10.0 10.0 100.0% 0 5.86s 7,302 392 2,387
GPT-6 Astra 10.0 10.0 100.0% 0 14.64s 7,302 395 8,298

Quick Compare

Switch Comparison Pair