AI BENCHY
Advertise here
#15

GPT-5.3-Codex

OpenAI Release: 2026-02-05 Tested on: 2026-05-22 00:19 openai/gpt-5.3-codex::medium

Summary

GPT-5.3-Codex scores 8.3 on AI BENCHY and ranks #15. It has 10.0 reliability, a 81.7% pass rate, $0.685 total cost, and 15.97s average response time.

Score

8.3

Consistency

8.4

Reliability

10.0

Total Cost (Current Price)

$0.685

Total Output Tokens

44,948

Total Input Tokens

0

Input Price

$1.750 / 1M

Output Price

$14.000 / 1M

Tests Correct

Wrong Tests: 6

Attempt pass rate: 81.7%

Flaky tests

4

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

Response Time (avg)

15.97s

Response Time (max): 100.93s

Response Time (total): 319.30s

Wrong answer: 4 Did not follow instructions: 2

Generation showcase

Hamster playing table tennis

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

#15 GPT-5.3-Codex

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

Run history

Tested on Score Reliability Tests Correct Total Cost Compare
2026-06-04 13:45 New test added 8.4 10.0 $0.740 Compare
2026-05-22 00:19 Re-test 8.3 10.0 $0.685 Current run
2026-04-11 01:44 First recorded run 8.6 N/A $0.573 Compare

Run comparison

RunScoreConsistencyReliabilityTests CorrectFlaky testsTotal Output TokensTotal Input TokensTotal CostResponse Time (avg)
2026-05-22 00:19 · Re-test8.38.410.014/20444,9480$0.68515.97s
2026-04-11 01:44 · First recorded run8.68.7N/A13/18337,4580$0.57315.38s
Difference-0.2-0.3+1+1+74900+$0.113+581ms

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-5.3-CodexmediumvsGPT-5.5mediumGPT-5.3-CodexmediumvsQwen3.6 Max PreviewmediumGPT-5.3-CodexmediumvsGemini 3.5 FlashmediumGPT-5.3-CodexmediumvsClaude Opus 4.8mediumGPT-5.3-CodexmediumvsGemini 3.1 Pro PreviewmediumGPT-5.3-CodexmediumvsClaude Opus 4.7mediumGPT-5.3-CodexmediumvsGemini 3.5 FlashhighGPT-5.3-CodexmediumvsGemini 3 Flash PreviewmediumGPT-5.3-CodexmediumvsNemotron 3 Ultra 550b A55bmediumFree AvailableGPT-5.3-CodexmediumvsGPT-5.5low

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 8.7 7.9
Coding 10.0 10.0
Combined 10.0 10.0
Data parsing and extraction 10.0 10.0
Domain specific 5.9 7.2
General Intelligence 4.6 10.0
Instructions following 10.0 10.0
Puzzle Solving 9.0 7.9
Tool Calling 10.0 10.0
Trivia 2.8 1.6

Compared models