Navigate
AI BENCHY
Advertise here

Nemotron 3 Ultra vs GPT-5.4 Mini

Nemotron 3 Ultra leads on average score with 6.1 vs 5.9. GPT-5.4 Mini has the lower benchmark cost at $0.095 vs $0.095. GPT-5.4 Mini is faster at 1.53s vs 3.87s, with pass rates of 42.4% vs 33.3%.

Last updated at: 2026-07-28

Rank
#144
Total Output Tokens
9,474
Response Time (avg)
3.87s
Total Cost
$0.095
Rank
#153
Total Output Tokens
7,880
Response Time (avg)
1.53s
Total Cost
$0.095
Recommended model GPT-5.4 Mini

Its score stays close to the best score here (5.9 vs 6.1), while responding about 2.5x faster than Nemotron 3 Ultra.

Detailed comparison

Metric Nemotron 3 Ultra Nemotron 3 Ultra none Release: 2026-06-04 Free Available GPT-5.4 Mini GPT-5.4 Mini none Release: 2026-03-17
Score 6.1 5.9
Rank #144 #153
Reliability 10.0 10.0
Consistency 9.3 8.9
Tests Correct
Attempt pass rate 42.4% 33.3%
Flaky tests 2 3
Total Runs 66 66
Cost per result 0.000 1.580
Total Cost $0.095 $0.095
Input Price $0.600 / 1M $0.750 / 1M
Output Price $3.600 / 1M $4.500 / 1M
Total Input Tokens 101,275 79,067
Output Tokens 9,474 7,880
Reasoning Tokens 0 0
Response Time (avg) 3.87s 1.53s
Response Time (max) 37.50s 9.92s
Response Time (total) 85.15s 33.74s

Model generation showcase

Hamster playing table tennis

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

#144 Nemotron 3 Ultra

none
Cost
$0.000
Time
149.6s
Tokens
3,405 tok

#153 GPT-5.4 Mini

none
Cost
$0.010
Time
11.7s
Tokens
2,151 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
Nemotron 3 Ultra 5.5 10.0 33.3% 0 1.02s 7,623 369 0
GPT-5.4 Mini 5.5 10.0 33.3% 0 913ms 7,305 401 0

Quick Compare

Switch Comparison Pair