AI BENCHY
Advertise here
#131

GPT-5.4 Mini

OpenAI Release: 2026-03-17 Tested on: 2026-06-04 13:45 openai/gpt-5.4-mini::none
(medium) (none)

Summary

GPT-5.4 Mini scores 5.3 on AI BENCHY and ranks #131. It has 10.0 reliability, a 30.2% pass rate, $0.038 total cost, and 1.13s average response time.

Score

5.3

Consistency

8.8

Reliability

10.0

Total Cost (Current Price)

$0.038

Total Output Tokens

2,541

Total Input Tokens

34,244

Input Price

$0.750 / 1M

Output Price

$4.500 / 1M

Tests Correct

Wrong Tests: 16

Attempt pass rate: 30.2%

Flaky tests

3

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

Response Time (avg)

1.13s

Response Time (max): 2.52s

Response Time (total): 23.82s

Wrong answer: 13 Did not follow instructions: 3

Generation showcase

Hamster playing table tennis

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

#131 GPT-5.4 Mini

none
Cost
$0.010
Time
11.7s
Tokens
2,151 tok

Run history

Tested on Score Reliability Tests Correct Total Cost Compare
2026-06-04 13:45 New test added 4.9 10.0 $0.038 Current run
2026-05-22 00:18 Suite changed 4.9 10.0 $0.035 Compare
2026-04-11 01:44 First recorded run 5.1 N/A $0.032 Compare

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

Price History

Historical pricing data for this model from OpenRouter.

Date Input Price Output Price
2026-06-04 15:40 $0.750 / 1M $4.500 / 1M

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

GPT-5.4 MininonevsQwen3.6 FlashnoneGPT-5.4 MininonevsQwen3.6 Max PreviewnoneGPT-5.4 MininonevsQwen3.5-35B-A3BnoneGPT-5.4 MininonevsQwen3.5-27BnoneGPT-5.4 MininonevsGemini 3.5 FlashhighGPT-5.4 MininonevsGemini 3 Flash PreviewmediumGPT-5.4 MininonevsNemotron 3 Ultra 550b A55bmediumFree AvailableGPT-5.4 MininonevsGPT-5.5low

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 3.1 8.1
Coding 5.5 10.0
Combined 3.0 10.0
Data parsing and extraction 10.0 10.0
Domain specific 3.5 4.4
General Intelligence 4.8 10.0
Instructions following 6.3 10.0
Puzzle Solving 5.4 10.0
Tool Calling 3.0 10.0
Trivia 3.0 10.0

Compared models