Navigate
Advertise here

GPT-6.1 Sol (xhigh) vs GPT-6.2 Sol (high)

The average score is effectively tied at 9.9 vs 9.8. GPT-6.2 Sol (high) has the lower benchmark cost at $0.726 vs $1.377. GPT-6.2 Sol (high) is faster at 10.48s vs 33.11s, with pass rates of 97.1% vs 97.1%.

Last updated at: 2026-11-17

Compared models

Rank
#12
Total Output Tokens
102,482
Response Time (avg)
33.11s
Total Cost
$1.377
Rank
#15
Total Output Tokens
40,847
Response Time (avg)
10.48s
Total Cost
$0.726
Recommended model GPT-6.2 Sol (high)

It has the best score here (9.8), while costing about 1.9x less than GPT-6.1 Sol (xhigh).

Detailed comparison

Metric GPT-6.1 Sol GPT-6.1 Sol xhigh Release: 2026-09-29 GPT-6.2 Sol GPT-6.2 Sol high Release: 2026-11-17
Score 9.9 9.8
Rank #12 #15
Reliability 10.0 10.0
Consistency 9.6 9.4
Attempts 69/69 69/69
Tests Correct
Attempt pass rate 97.1% 97.1%
Flaky tests 1 2
Total Runs 69 69
Cost per result 6.256 3.455
Total Cost $1.377 $0.726
Input Price $2.000 / 1M $2.000 / 1M
Output Price $10.000 / 1M $10.000 / 1M
Cache Read Price $0.100 / 1M $0.100 / 1M
Cache Write Price $2.500 / 1M $2.500 / 1M
Total Input Tokens 175,712 158,484
Output Tokens 5,640 5,575
Reasoning Tokens 96,842 35,272
Response Time (avg) 33.11s 10.48s
Response Time (max) 491.85s 95.42s
Response Time (total) 761.52s 241.15s
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.

#12 GPT-6.1 Sol

xhigh
Cost
$0.147
Time
279.4s
Tokens
14,790 tok

#15 GPT-6.2 Sol

high
Cost
$0.043
Time
20.8s
Tokens
4,347 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 10.65s 7,302 393 4,483
GPT-6.2 Sol 10.0 10.0 100.0% 0 5.87s 7,302 396 2,883

Switch Comparison Pair