Advertise here
#71

GPT-5.4

OpenAI Release: 2026-03-05 Tested on: 2026-04-11 01:44 openai/gpt-5.4::none
~1.5T total (~100B active)MoEClosedEstimated
(medium) (none)

Summary

GPT-5.4 scores 5.9 on AI BENCHY and ranks #71. It has N/A reliability, a 42.6% pass rate, $0.104 total cost, and 1.51s average response time.

What makes GPT-5.4 unique: Its total benchmark cost is unusually low for its score range. It is notably fast compared with similar models.

Model facts

Researched on 2026-08-12

Estimated
Parameters
~1.5T total (~100B active)
Architecture
MoE
Availability
Closed
License
-

Best estimate from public evidence; the vendor did not disclose every value. Vendor does not disclose the architecture or count.

Parameter source Availability source

Score

5.9

Consistency

9.1

Reliability

N/A

Total Cost (Current Price)

$0.104

Total Output Tokens

2,317

Total Input Tokens

0

Input Price

$2.500 / 1M

Output Price

$15.000 / 1M

Tests Correct

Wrong Tests: 11

Attempt pass rate: 42.6%

Flaky tests

2

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

Response Time (avg)

1.51s

Response Time (max): 2.95s

Response Time (total): 27.21s

Wrong answer: 10 Did not follow instructions: 1

Hamster playing table tennis

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

#71 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
2026-08-14 02:13 Re-test 5.8 10.0 $0.397 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 Compare
2026-04-11 01:44 First recorded run 5.9 N/A $0.104 Current run

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-5.4nonevsSeed 2.1 TurbononeGPT-5.4nonevsSolar Pro 4noneGPT-5.4nonevsGPT-5.4 MininoneGPT-5.4nonevsNorth Mini CodemediumFree AvailableGPT-5.4nonevsGLM 5.3 FlashlowGPT-5.4nonevsNemotron 3 SupermediumFree AvailableGPT-5.4nonevsDots 3 Note PreviewmediumFree AvailableGPT-5.4nonevsGLM 5noneGPT-5.4nonevsStep 3.5 FlashmediumGPT-5.4nonevsInkling Smalllow

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 3.2 8.0
Coding 10.0 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

Compared models