Navigate
Advertise here

GPT-5.6 Terra (high) vs GPT-6 Luna (high)

GPT-6 Luna (high) leads on average score with 8.3 vs 8.0. GPT-6 Luna (high) has the lower benchmark cost at $0.054 vs $0.836. GPT-5.6 Terra (high) is faster at 11.22s vs 17.53s, with pass rates of 68.2% vs 75.8%.

Last updated at: 2026-09-23

Compared models

Rank
#88
Total Output Tokens
56,088
Response Time (avg)
11.22s
Total Cost
$0.836
Rank
#73
Total Output Tokens
91,405
Response Time (avg)
17.53s
Total Cost
$0.054
Recommended model GPT-6 Luna (high)

It has the best score here (8.3), while costing about 15.5x less than GPT-5.6 Terra (high).

Detailed comparison

Metric GPT-5.6 Terra GPT-5.6 Terra high Release: 2026-07-09 GPT-6 Luna GPT-6 Luna high Release: 2026-09-23
Score 8.0 8.3
Rank #88 #73
Reliability 10.0 10.0
Consistency 9.3 9.0
Attempts 66/66 66/66
Tests Correct
Attempt pass rate 68.2% 75.8%
Flaky tests 2 3
Total Runs 66 66
Cost per result 7.293 0.359
Total Cost $0.836 $0.054
Input Price $2.000 / 1M $0.100 / 1M
Output Price $12.000 / 1M $0.500 / 1M
Total Input Tokens 81,056 80,441
Output Tokens 5,055 4,761
Reasoning Tokens 51,033 86,644
Response Time (avg) 11.22s 17.53s
Response Time (max) 91.49s 106.93s
Response Time (total) 246.77s 385.74s
Parameters ~1T total (~60B active) ~400B total (~17B active)
Availability Closed Closed

Model generation showcase

Hamster playing table tennis

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

#88 GPT-5.6 Terra

high
Cost
$0.055
Time
30.2s
Tokens
3,748 tok

#73 GPT-6 Luna

high
Cost
$0.003
Time
49.2s
Tokens
5,231 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-5.6 Terra 7.6 7.2 77.8% 1 9.14s 7,302 370 6,087
GPT-6 Luna 7.8 7.4 77.8% 1 24.69s 7,302 483 15,691

Quick Compare

Switch Comparison Pair