Navigate
Advertise here

Compared models

GPT-5.4 (medium) vs GPT-5.3-Codex (medium) vs GPT-5.2 (medium) benchmark comparison: GPT-5.3-Codex (medium) leads on Score with 8.9. GPT-5.4 (medium) leads on Reliability with 10.0. GPT-5.3-Codex (medium) has the lowest Total Cost at $0.988. GPT-5.3-Codex (medium) is fastest at 16.91s.

Last updated at: 2026-09-24

Compared models

Rank
#56
Total Output Tokens
90,466
Response Time (avg)
22.85s
Total Cost
$1.560
Rank
#37
Total Output Tokens
60,374
Response Time (avg)
16.91s
Total Cost
$0.988
Rank
#64
Total Output Tokens
71,252
Response Time (avg)
28.51s
Total Cost
$1.182
Recommended model GPT-5.3-Codex (medium)

It has the best score here (8.9), while responding about 1.5x faster than the other models in this comparison.

Detailed comparison

Metric GPT-5.4 GPT-5.4 medium Release: 2026-03-05 GPT-5.3-Codex GPT-5.3-Codex medium Release: 2026-02-05 GPT-5.2 GPT-5.2 medium Release: 2025-12-11
Score 8.5 8.9 8.4
Rank #56 #37 #64
Reliability 10.0 10.0 10.0
Consistency 8.6 8.6 8.5
Attempts 66/66 66/66 66/66
Tests Correct
Attempt pass rate 77.3% 83.3% 72.7%
Flaky tests 4 4 4
Total Runs 66 66 66
Cost per result 10.399 6.171 8.438
Total Cost $1.560 $0.988 $1.182
Input Price $2.500 / 1M $1.750 / 1M $1.750 / 1M
Output Price $15.000 / 1M $14.000 / 1M $14.000 / 1M
Total Input Tokens 81,136 81,187 105,013
Output Tokens 6,155 6,258 9,914
Reasoning Tokens 84,311 54,116 61,338
Response Time (avg) 22.85s 16.91s 28.51s
Response Time (max) 100.41s 100.93s 116.86s
Response Time (total) 502.78s 372.03s 456.13s
Parameters ~1.5T total (~100B active) ~1.2T total (~80B active) ~1.2T total (~80B active)
Availability Closed Closed Closed

Model generation showcase

Hamster playing table tennis

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

#56 GPT-5.4

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

#37 GPT-5.3-Codex

medium
Cost
$0.049
Time
54.9s
Tokens
3,580 tok

#64 GPT-5.2

medium
Cost
$0.047
Time
49.2s
Tokens
3,396 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-5.4 8.8 7.8 88.9% 1 44.36s 7,305 433 24,216
GPT-5.3-Codex 10.0 10.0 100.0% 0 19.50s 7,302 535 10,890
GPT-5.2 10.0 10.0 100.0% 0 22.73s 7,302 511 11,912

Quick Compare

Switch Comparison Pair