AI BENCHY
Advertise here
#5

GPT-5.5

OpenAI Release: 2026-04-24 Tested on: 2026-04-24 20:23 openai/gpt-5.5::medium
(medium) (low) (none)

Summary

GPT-5.5 scores 9.0 on AI BENCHY and ranks #5. It has N/A reliability, a 87.0% pass rate, $2.884 total cost, and 32.75s average response time.

What makes GPT-5.5 unique: It is one of the highest-ranked models overall.

Score

9.0

Consistency

9.2

Reliability

N/A

Total Cost (Current Price)

$2.884

Total Output Tokens

91,552

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

2

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

Response Time (avg)

32.75s

Response Time (max): 332.10s

Response Time (total): 589.59s

Wrong answer: 2 Did not follow instructions: 1

Generation showcase

Hamster playing table tennis

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

#5 GPT-5.5

medium
Cost
$0.112
Time
71.9s
Tokens
3,807 tok

Run history

Tested on Score Reliability Tests Correct Total Cost Compare
2026-06-04 13:48 New test added 8.8 10.0 $3.679 Compare
2026-05-22 00:21 Suite changed 8.7 10.0 $3.503 Compare
2026-04-24 20:23 Initial run 9.0 N/A $2.884 Current run

Run comparison

RunScoreConsistencyReliabilityTests CorrectFlaky testsTotal Output TokensTotal Input TokensTotal CostResponse Time (avg)
2026-04-24 20:23 · Initial run9.09.2N/A15/18291,5520$2.88432.75s
2026-06-04 13:48 · New test added8.88.910.017/213116,91034,212$3.67937.98s
Difference+0.2+0.3-2-1-25358-34212-$0.795-5226ms

These two runs used different benchmark suites, so the deltas reflect both model changes and suite changes.

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-5.5mediumvsGemini 3.5 FlashmediumGPT-5.5mediumvsGPT-5.5lowGPT-5.5mediumvsClaude Opus 4.8mediumGPT-5.5mediumvsQwen3.7 MaxmediumGPT-5.5mediumvsClaude Opus 4.7mediumGPT-5.5mediumvsGemini 3 Flash PreviewmediumGPT-5.5mediumvsGemini 3.5 FlashhighGPT-5.5mediumvsNemotron 3 Ultra 550b A55bmediumFree AvailableGPT-5.5mediumvsGemini 3.5 Flashlow

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 7.2
General Intelligence 10.0 10.0
Instructions following 10.0 10.0
Puzzle Solving 8.6 7.9
Tool Calling 10.0 10.0

Compared models