Navigate
AI BENCHY
Advertise here

GPT-5.4 Nano (medium) vs GPT-5.6 Luna (medium)

The average score is effectively tied at 7.5 vs 7.6. GPT-5.4 Nano (medium) has the lower benchmark cost at $0.138 vs $0.352. GPT-5.6 Luna (medium) is faster at 7.28s vs 13.24s, with pass rates of 65.2% vs 65.2%.

Last updated at: 2026-07-25

Rank
#61
Total Output Tokens
97,122
Response Time (avg)
13.24s
Total Cost
$0.138
Rank
#57
Total Output Tokens
43,679
Response Time (avg)
7.28s
Total Cost
$0.352
Recommended model GPT-5.4 Nano (medium)

It has the best score here (7.5), while costing about 2.5x less than GPT-5.6 Luna (medium).

Detailed comparison

Metric GPT-5.4 Nano GPT-5.4 Nano medium Release: 2026-03-17 GPT-5.6 Luna GPT-5.6 Luna medium Release: 2026-07-09
Score 7.5 7.6
Rank #61 #57
Reliability 10.0 10.0
Consistency 8.5 9.6
Tests Correct
Attempt pass rate 65.2% 65.2%
Flaky tests 4 1
Total Runs 66 66
Cost per result 1.150 2.513
Total Cost $0.138 $0.352
Input Price $0.200 / 1M $1.000 / 1M
Output Price $1.250 / 1M $6.000 / 1M
Total Input Tokens 82,819 89,676
Output Tokens 7,100 5,699
Reasoning Tokens 90,022 37,980
Response Time (avg) 13.24s 7.28s
Response Time (max) 94.06s 29.85s
Response Time (total) 291.33s 160.27s

Hamster playing table tennis

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

#61 GPT-5.4 Nano

medium
Cost
$0.007
Time
24.6s
Tokens
4,943 tok

#57 GPT-5.6 Luna

medium
Cost
$0.014
Time
14.6s
Tokens
2,362 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-5.4 Nano 6.1 4.7 66.7% 2 19.12s 7,305 516 20,778
GPT-5.6 Luna 5.4 7.2 44.4% 1 10.38s 7,302 564 9,928

Quick Compare

Switch Comparison Pair