AI BENCHY
AD
Track all your projects in one dashboard. Get 📊stats, 🔥heatmaps and 👀recordings in one self-hosted dashboard.
uxwizz.com
#94

GPT-5 Nano

OpenAI Release: 2025-08-07 Tested on: 2026-05-22 00:17 openai/gpt-5-nano::medium

Summary

GPT-5 Nano scores 6.1 on AI BENCHY and ranks #94. It has 10.0 reliability, a 55.0% pass rate, $0.076 total cost, and 43.11s average response time.

What makes GPT-5 Nano unique: It stands out most in Combined, where it ranks #1, while Data parsing and extraction is its weakest area at #14. It uses unusually many reasoning tokens, which can help explain its slower or more expensive runs.

Score

6.1

Consistency

7.1

Reliability

10.0

Total Cost (Current Price)

$0.076

Total Output Tokens

184,922

Total Input Tokens

0

Input Price

$0.050 / 1M

Output Price

$0.400 / 1M

Tests Correct

Wrong Tests: 12

Attempt pass rate: 55.0%

Flaky tests

7

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

Response Time (avg)

43.11s

Response Time (max): 204.02s

Response Time (total): 560.45s

Wrong answer: 9 Did not follow instructions: 2 Timed out: 1

Generation showcase

Hamster playing table tennis

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

#94 GPT-5 Nano

medium
Cost
$0.006
Time
108.5s
Tokens
13,209 tok

Run history

Tested on Score Reliability Tests Correct Total Cost Compare
2026-06-04 13:44 New test added 6.3 10.0 $0.081 Compare
2026-05-22 00:17 Suite changed 6.1 10.0 $0.076 Current run
2026-04-11 01:44 First recorded run 6.3 N/A $0.066 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

GPT-5 NanomediumvsGemini 3.5 FlashminimalGPT-5 NanomediumvsQwen3.7 MaxnoneGPT-5 NanomediumvsRing-2.6-1TmediumGPT-5 NanomediumvsGemini 3 Flash PreviewnoneGPT-5 NanomediumvsGemini 3.5 FlashhighGPT-5 NanomediumvsGemini 3 Flash PreviewmediumGPT-5 NanomediumvsNemotron 3 Ultra 550b A55bmediumFree AvailableGPT-5 NanomediumvsGPT-5.5low

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 6.5 7.9
Coding 5.4 6.6
Combined 10.0 10.0
Data parsing and extraction 3.7 1.7
Domain specific 5.2 4.4
General Intelligence 4.1 10.0
Instructions following 9.8 10.0
Puzzle Solving 5.3 7.2
Tool Calling 10.0 10.0
Trivia 3.0 10.0

Compared models