AI BENCHY
Advertise here
#5

GPT-5.5

OpenAI Release: 2026-04-24 Tested on: 2026-04-26 10:23 openai/gpt-5.5::low
(medium) (low) (none)

Summary

GPT-5.5 scores 9.0 on AI BENCHY and ranks #5. It has 10.0 reliability, a 87.0% pass rate, $0.681 total cost, and 8.39s average response time.

What makes GPT-5.5 unique: It is one of the highest-ranked models overall. Its total benchmark cost is unusually low for its score range. It is notably fast compared with similar models.

Score

9.0

Consistency

9.6

Reliability

10.0

Total Cost (Current Price)

$0.681

Total Output Tokens

18,093

Total Input Tokens

0

Input Price

$5.000 / 1M

Output Price

$30.000 / 1M

Tests Correct

Wrong Tests: 3

Attempt pass rate: 87.0%

Flaky tests

1

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

Response Time (avg)

8.39s

Response Time (max): 56.19s

Response Time (total): 151.01s

Wrong answer: 2 Did not follow instructions: 1

Hamster playing table tennis

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

#5 GPT-5.5

low
Cost
$0.068
Time
37.0s
Tokens
2,339 tok

Run history

Tested on Score Reliability Tests Correct Total Cost Compare
2026-07-16 22:35 New test added 9.3 10.0 $1.253 Compare
2026-06-04 13:47 New test added 9.0 10.0 $0.907 Compare
2026-05-22 13:31 Suite changed 8.9 10.0 $0.822 Compare
2026-05-08 15:31 Suite changed 8.9 10.0 $0.706 Compare
2026-04-26 10:23 Initial run 9.0 10.0 $0.681 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-5.5lowvsGPT-5.6 SolhighGPT-5.5lowvsGemini 3.1 Pro PreviewmediumGPT-5.5lowvsGPT-5.6 SolmediumGPT-5.5lowvsClaude Opus 5highGPT-5.5lowvsGemini 3.6 FlashlowGPT-5.5lowvsClaude Opus 5mediumGPT-5.5lowvsGPT-5.6 SollowGPT-5.5lowvsQwen3.7 MaxmediumGPT-5.5lowvsGemini 3.5 FlashhighGPT-5.5lowvsGemini 3.5 Flashmedium

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 10.0 10.0
Coding 10.0 10.0
Combined 10.0 10.0
Data parsing and extraction 10.0 10.0
Domain specific 5.3 10.0
General Intelligence 10.0 10.0
Instructions following 9.9 10.0
Puzzle Solving 9.0 7.9
Tool Calling 10.0 10.0

Compared models