Navigate
AI BENCHY
Advertise here

GPT-5.2 (medium) vs GPT-5.4 (medium)

GPT-5.4 (medium) leads on average score with 8.5 vs 8.4. GPT-5.2 (medium) has the lower benchmark cost at $1.182 vs $1.560. GPT-5.4 (medium) is faster at 22.85s vs 28.51s, with pass rates of 72.7% vs 77.3%.

Last updated at: 2026-09-02

Rank
#48
Total Output Tokens
71,252
Response Time (avg)
28.51s
Total Cost
$1.182
Rank
#43
Total Output Tokens
90,466
Response Time (avg)
22.85s
Total Cost
$1.560
Recommended model GPT-5.4 (medium)

It has the strongest score in this comparison (8.5) and the best overall balance of cost and response time across all 2 models.

Detailed comparison

Metric GPT-5.2 GPT-5.2 medium Release: 2025-12-11 GPT-5.4 GPT-5.4 medium Release: 2026-03-05
Score 8.4 8.5
Rank #48 #43
Reliability 10.0 10.0
Consistency 8.5 8.6
Attempts 66/66 66/66
Tests Correct
Attempt pass rate 72.7% 77.3%
Flaky tests 4 4
Total Runs 66 66
Cost per result 8.438 10.399
Total Cost $1.182 $1.560
Input Price $1.750 / 1M $2.500 / 1M
Output Price $14.000 / 1M $15.000 / 1M
Total Input Tokens 105,013 81,136
Output Tokens 9,914 6,155
Reasoning Tokens 61,338 84,311
Response Time (avg) 28.51s 22.85s
Response Time (max) 116.86s 100.41s
Response Time (total) 456.13s 502.78s
Parameters ~1.2T total (~80B active) ~1.5T total (~100B active)
Availability Closed Closed

Model generation showcase

Hamster playing table tennis

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

#48 GPT-5.2

medium
Cost
$0.047
Time
49.2s
Tokens
3,396 tok

#43 GPT-5.4

medium
Cost
$0.214
Time
199.6s
Tokens
14,349 tok

Top Models by Score

Score vs Total Cost

Response Time (avg)

Score vs Response Time (avg)

Total Output Tokens

Score vs Total Output Tokens

Category Breakdown

Coding Score Consistency Attempt pass rate Flaky tests Tests Correct Response Time (avg) Input Tokens Output Tokens Reasoning Tokens
GPT-5.2 10.0 10.0 100.0% 0 22.73s 7,302 511 11,912
GPT-5.4 8.8 7.8 88.9% 1 44.36s 7,305 433 24,216

Quick Compare

Switch Comparison Pair

GPT-5.2mediumvsQwen3.8 27BhighGPT-5.2mediumvsGrok 4.5lowGPT-5.2mediumvsInkling SmallhighGPT-5.4mediumvsQwen3.8 MaxlowMuse Spark 1.2lowvsGPT-5.2mediumMuse Spark 1.2lowvsGPT-5.4mediumMuse Spark 1.1lowvsGPT-5.2mediumGPT-5.4mediumvsGrok 4.5lowGPT-5.4mediumvsQwen3.8 27BhighMuse Spark 1.2highvsGPT-5.4mediumGPT-5.4mediumvsInkling SmallhighGPT-5.2mediumvsQwen3.8 Maxlow