AI BENCHY
Advertise here
#24

GPT-5.2 Chat

OpenAI Release: 2025-12-11 Tested on: 2026-06-04 13:47 openai/gpt-5.2-chat::none

Summary

GPT-5.2 Chat scores 7.9 on AI BENCHY and ranks #24. It has 10.0 reliability, a 74.6% pass rate, $0.393 total cost, and 7.13s average response time.

What makes GPT-5.2 Chat unique: Its total benchmark cost is unusually low for its score range. It is notably fast compared with similar models.

Score

7.9

Consistency

8.9

Reliability

10.0

Total Cost (Current Price)

$0.393

Total Output Tokens

23,744

Total Input Tokens

34,212

Input Price

$1.750 / 1M

Output Price

$14.000 / 1M

Tests Correct

Wrong Tests: 7

Attempt pass rate: 74.6%

Flaky tests

3

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

Response Time (avg)

7.13s

Response Time (max): 38.52s

Response Time (total): 149.69s

Wrong answer: 6 Did not follow instructions: 1

Hamster playing table tennis

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

#24 GPT-5.2 Chat

none
Cost
$0.010
Time
15.3s
Tokens
797 tok

Run history

Tested on Score Reliability Tests Correct Total Cost Compare
2026-07-16 22:40 New test added 8.0 10.0 $0.604 Compare
2026-06-04 13:47 New test added 7.9 10.0 $0.393 Current run
2026-05-22 00:19 Suite changed 7.6 10.0 $0.355 Compare
2026-04-11 01:44 First recorded run 7.9 N/A $0.291 Compare

This run used a different benchmark suite. Keep suite changes in mind when reading historical movement.

Price History

Historical pricing data for this model from OpenRouter.

Date Input Price Output Price
2026-06-04 14:42 $1.750 / 1M $14.000 / 1M

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-5.2 ChatnonevsStep 3.7 FlashmediumGPT-5.2 ChatnonevsGLM 5.2highGPT-5.2 ChatnonevsMuse Spark 1.1highGPT-5.2 ChatnonevsKimi K3maxGPT-5.2 ChatnonevsGPT-5 MinimediumGPT-5.2 ChatnonevsGPT-5.6 TerrahighGPT-5.2 ChatnonevsGemini 3 Flash PreviewmediumGPT-5.2 ChatnonevsGemini 3.5 FlashhighGPT-5.2 ChatnonevsNemotron 3 UltramediumFree AvailableGPT-5.2 ChatnonevsGPT-5.5low

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 8.7 7.9
Coding 8.8 7.8
Combined 10.0 10.0
Data parsing and extraction 10.0 10.0
Domain specific 5.3 10.0
General Intelligence 4.4 3.0
Instructions following 9.8 10.0
Puzzle Solving 7.7 10.0
Tool Calling 10.0 10.0
Trivia 3.0 10.0

Compared models