AI BENCHY
AD
Track all your projects in one dashboard. Get 📊stats, 🔥heatmaps and 👀recordings in one self-hosted dashboard.
uxwizz.com
#113

GPT-5.4

OpenAI Release: 2026-03-05 Tested on: 2026-05-22 00:18 openai/gpt-5.4::none
(medium) (none)

Summary

GPT-5.4 scores 5.6 on AI BENCHY and ranks #113. It has 10.0 reliability, a 38.3% pass rate, $0.115 total cost, and 1.46s average response time.

What makes GPT-5.4 unique: It stands out most in Coding, where it ranks #1, while Anti-AI Tricks is its weakest area at #13. It is notably fast compared with similar models.

Score

5.6

Consistency

9.1

Total Output Tokens

2,378

Total Input Tokens

0

Input Price

$2.500 / 1M

Output Price

$15.000 / 1M

Tests Correct

Wrong Tests: 13

Attempt pass rate: 38.3%

Flaky tests

2

Flaky tests had mixed outcomes across runs (at least one pass and one fail).

Response Time (avg)

1.46s

Response Time (max): 2.95s

Response Time (total): 29.23s

Hamster playing table tennis

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

#113 GPT-5.4

none
Cost
$0.026
Time
18.1s
Tokens
1,792 tok

Run history

Tested on Score Reliability Tests Correct Total Cost Compare
2026-07-16 22:33 New test added 5.8 10.0 $0.397 Compare
2026-06-04 13:45 New test added 5.5 10.0 $0.122 Compare
2026-05-22 00:18 Suite changed 5.6 10.0 $0.115 Current run
2026-04-11 01:44 First recorded run 5.9 N/A $0.104 Compare

This run used a different benchmark suite. Keep suite changes in mind when reading historical movement.

Charts

Choose the first model, then click a second model to open a side-by-side page.

Total Output Tokens

Score vs Total Output Tokens

Quick Compare

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 3.2 8.0
Coding 6.8 10.0
Combined 3.0 10.0
Data parsing and extraction 10.0 10.0
Domain specific 5.3 7.2
General Intelligence 4.4 9.9
Instructions following 6.5 10.0
Puzzle Solving 5.6 9.8
Tool Calling 10.0 10.0
Trivia 3.0 10.0

Compared models