AI BENCHY
Your ad here

#73

GPT-5.4 Nano

OpenAI · Release: 2026-03-17 · openai/gpt-5.4-nano::none

Score

4.3

Cost per result

0.404

Consistency

7.3

Total Cost

$0.009

Tests Correct

Wrong Tests: 15

Attempt pass rate: 29.4%

Flaky tests

6

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

Response Time (avg)

1.39s

Response Time (max): 3.84s

Response Time (total): 23.70s

Wrong answer: 12 Did not follow instructions: 3

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 NanononevsGrok 4.1 FastnoneGPT-5.4 NanononevsQwen3.5-9BmediumGPT-5.4 NanononevsGLM 4.7 FlashmediumGPT-5.4 NanononevsGemini 3 Flash PreviewmediumGPT-5.4 NanononevsGemini 3.1 Pro PreviewmediumGPT-5.4 NanononevsStep 3.5 FlashmediumFree Available

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 3.5 8.0
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 5.0 6.8
Puzzle Solving 3.7 7.3
Tool Calling 10.0 10.0

Compared models