Navigate
AI BENCHY
Advertise here

OpenAI: GPT-5.3 Chat vs OpenAI: GPT-5.4 Mini

The average score is effectively tied at 7.5 vs 7.5. GPT-5.3 Chat has the lower benchmark cost at $0.571 vs $0.756. GPT-5.3 Chat is faster at 6.88s vs 25.94s, with pass rates of 68.2% vs 71.2%.

Recommended modelGPT-5.3 ChatIt has the best score here (7.5), while responding about 3.8x faster than GPT-5.4 Mini (medium).

Last updated at: 2026-07-17

Metric GPT-5.3 Chat GPT-5.3 Chat none Release: 2026-03-03 GPT-5.4 Mini GPT-5.4 Mini medium Release: 2026-03-17
Score 7.5 7.5
Rank #52 #54
Reliability 10.0 10.0
Consistency 8.2 7.7
Tests Correct
Attempt pass rate 68.2% 71.2%
Flaky tests 5 6
Total Runs 66 66
Cost per result 4.387 6.299
Total Cost $0.571 $0.756
Input Price $1.750 / 1M $0.750 / 1M
Output Price $14.000 / 1M $4.500 / 1M
Total Input Tokens 78,990 97,155
Output Tokens 30,854 6,211
Reasoning Tokens 0 145,544
Response Time (avg) 6.88s 25.94s
Response Time (max) 18.33s 138.75s
Response Time (total) 151.31s 570.66s

Hamster playing table tennis

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

#52 GPT-5.3 Chat

none
Cost
$0.008
Time
8.1s
Tokens
634 tok

#54 GPT-5.4 Mini

medium
Cost
$0.056
Time
95.5s
Tokens
12,464 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-5.3 Chat 5.6 4.7 55.6% 2 10.52s 7,302 6,632 0
GPT-5.4 Mini 8.4 7.4 88.9% 1 57.87s 7,305 467 40,902

Quick Compare

Switch Comparison Pair