Navigate
Advertise here

GPT-6.1 Sol (max) vs GPT-6.2 Astra (medium)

The average score is effectively tied at 9.9 vs 9.9. GPT-6.1 Sol (max) has the lower benchmark cost at $1.006 vs $1.632. GPT-6.2 Astra (medium) is faster at 6.65s vs 61.98s, with pass rates of 95.7% vs 98.6%.

Last updated at: 2026-11-17

Compared models

Rank
#10
Total Output Tokens
63,823
Response Time (avg)
61.98s
Total Cost
$1.006
Rank
#7
Total Output Tokens
9,593
Response Time (avg)
6.65s
Total Cost
$1.632
Recommended model GPT-6.2 Astra (medium)

It has the best score here (9.9), while responding about 9.3x faster than GPT-6.1 Sol (max).

Detailed comparison

Metric GPT-6.1 Sol GPT-6.1 Sol max Release: 2026-09-29 GPT-6.2 Astra GPT-6.2 Astra medium Release: 2026-11-17
Score 9.9 9.9
Rank #10 #7
Reliability 9.7 10.0
Consistency 10.0 9.6
Attempts 69/69 69/69
Tests Correct
Attempt pass rate 95.7% 98.6%
Flaky tests 0 1
Total Runs 69 69
Cost per result 4.571 7.415
Total Cost $1.006 $1.632
Input Price $2.000 / 1M $8.000 / 1M
Output Price $10.000 / 1M $40.000 / 1M
Cache Read Price $0.100 / 1M $0.400 / 1M
Cache Write Price $2.500 / 1M $10.000 / 1M
Total Input Tokens 183,607 155,927
Output Tokens 5,741 4,773
Reasoning Tokens 58,082 4,820
Response Time (avg) 61.98s 6.65s
Response Time (max) 960.01s 46.34s
Response Time (total) 1425.65s 153.03s
Parameters ~2T total (~150B active) ~2T total (~150B active)
Availability Closed Closed

Cache prices apply to input tokens. Reads reuse cached prompts; writes store them and can cost extra. Output tokens use the output price.

Model generation showcase

Hamster playing table tennis

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

#10 GPT-6.1 Sol

max
Cost
$0.272
Time
584.0s
Tokens
27,273 tok

#7 GPT-6.2 Astra

medium
Cost
$0.106
Time
26.0s
Tokens
2,719 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-6.1 Sol 10.0 10.0 100.0% 0 13.57s 7,302 398 7,668
GPT-6.2 Astra 10.0 10.0 100.0% 0 3.24s 7,302 382 811

Switch Comparison Pair