AI BENCHY
AD
Track all your projects in one dashboard. Get 📊stats, 🔥heatmaps and 👀recordings in one self-hosted dashboard.
uxwizz.com
#147

GPT-5.4 Nano

OpenAI Release: 2026-03-17 Tested on: 2026-05-22 00:19 openai/gpt-5.4-nano::none
(medium) (none)

Summary

GPT-5.4 Nano scores 4.5 on AI BENCHY and ranks #147. It has 10.0 reliability, a 30.0% pass rate, $0.010 total cost, and 1.33s average response time.

What makes GPT-5.4 Nano unique: It stands out most in Coding, where it ranks #2, while General Intelligence is its weakest area at #14. It is notably fast compared with similar models.

Score

4.5

Consistency

7.6

Total Output Tokens

2,804

Total Input Tokens

0

Input Price

$0.200 / 1M

Output Price

$1.250 / 1M

Tests Correct

Wrong Tests: 17

Attempt pass rate: 30.0%

Flaky tests

6

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

Response Time (avg)

1.33s

Response Time (max): 3.84s

Response Time (total): 26.66s

Generation showcase

Hamster playing table tennis

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

#147 GPT-5.4 Nano

none
Cost
$0.008
Time
46.1s
Tokens
5,735 tok

Run history

Tested on Score Reliability Tests Correct Total Cost Compare
2026-06-04 13:45 New test added 4.7 10.0 $0.011 Compare
2026-05-22 00:19 Suite changed 4.5 10.0 $0.010 Current run
2026-04-11 01:44 First recorded run 4.5 N/A $0.009 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 3.5 8.0
Coding 5.4 6.8
Combined 3.0 10.0
Data parsing and extraction 6.5 10.0
Domain specific 2.9 4.4
General Intelligence 3.8 2.5
Instructions following 6.3 10.0
Puzzle Solving 3.7 7.2
Tool Calling 10.0 10.0
Trivia 3.0 10.0

Compared models