AI BENCHY Compare

OpenAI: GPT-5.3 Chat vs xAI: Grok 4.20

Summary

GPT-5.3 Chat leads on average score with 7.5 vs 7.3. GPT-5.3 Chat has the lower benchmark cost at $0.433 vs $0.609. GPT-5.3 Chat is faster at 6.34s vs 27.68s, with pass rates of 66.7% vs 63.5%.

Recommended modelGPT-5.3 ChatIt has the best score here (7.5), while responding about 4.4x faster than Grok 4.20 (medium).

Last updated at: 2026-07-14

Metric	GPT-5.3 Chat GPT-5.3 Chat none Release: 2026-03-03	Grok 4.20 Grok 4.20 medium Release: 2026-03-31

Metric	GPT-5.3 Chat GPT-5.3 Chat none Release: 2026-03-03	Grok 4.20 Grok 4.20 medium Release: 2026-03-31
Score	7.5	7.3
Rank	#61	#69
Reliability	10.0	10.0
Consistency	8.1	8.8
Tests Correct
Attempt pass rate	66.7%	63.5%
Flaky tests	5	3
Total Runs	63	63
Cost per result	3.605	8.309
Total Cost	$0.433	$0.609
Input Price	$1.750 / 1M	$1.250 / 1M
Output Price	$14.000 / 1M	$2.500 / 1M
Total Input Tokens	34,209	44,433
Output Tokens	26,617	1,819
Reasoning Tokens	0	219,524
Response Time (avg)	6.34s	27.68s
Response Time (max)	18.33s	199.66s
Response Time (total)	133.13s	581.26s

Generation showcase

Hamster playing table tennis

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

#61 GPT-5.3 Chat

none

Cost: $0.008
Time: 8.1s
Tokens: 634 tok

#69 xAI: Grok 4.20

medium

Cost: $0.041
Time: 110.3s
Tokens: 16,336 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

Category:

Anti-AI Tricks	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
GPT-5.3 Chat	6.7	8.1	58.3%	1		3.86s	606	3,167	0
Grok 4.20	8.2	7.9	83.3%	1		3.95s	2,010	287	8,312

Coding	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
GPT-5.3 Chat	5.6	4.7	55.6%	2		10.52s	7,302	6,632	0
Grok 4.20	6.3	6.6	55.6%	1		109.93s	8,307	268	103,150

Combined	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
GPT-5.3 Chat	10.0	10.0	100.0%	0		11.96s	11,019	2,614	0
Grok 4.20	10.0	10.0	100.0%	0		17.40s	12,909	232	9,556

Data parsing and extraction	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
GPT-5.3 Chat	10.0	10.0	100.0%	0		2.21s	7,140	942	0
Grok 4.20	10.0	10.0	100.0%	0		4.17s	7,761	180	5,333

Domain specific	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
GPT-5.3 Chat	3.5	4.4	33.3%	2		13.01s	723	8,264	0
Grok 4.20	5.3	10.0	33.3%	0		27.03s	1,764	375	49,339

General Intelligence	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
GPT-5.3 Chat	4.6	10.0	0.0%	0		1.99s	477	319	0
Grok 4.20	3.9	2.6	33.3%	1		24.48s	825	65	6,440

Instructions following	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
GPT-5.3 Chat	9.8	10.0	100.0%	0		3.51s	660	1,491	0
Grok 4.20	9.8	10.0	100.0%	0		4.26s	1,362	57	6,419

Puzzle Solving	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
GPT-5.3 Chat	10.0	10.0	100.0%	0		2.99s	642	1,758	0
Grok 4.20	7.7	10.0	66.7%	0		6.22s	1,689	149	7,913

Tool Calling	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
GPT-5.3 Chat	10.0	10.0	100.0%	0		8.36s	5,445	861	0
Grok 4.20	3.0	10.0	0.0%	0		13.68s	7,275	197	6,620

Trivia	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
GPT-5.3 Chat	3.0	10.0	0.0%	0		4.38s	195	569	0
Grok 4.20	3.0	10.0	0.0%	0		63.48s	531	9	16,442

Quick Compare

Switch Comparison Pair

KAT-Coder-Pro V2.5mediumvsGPT-5.3 Chatnone Mercury 2mediumvsGPT-5.3 Chatnone Gemini 3 Flash PreviewlowvsGrok 4.20medium Kimi K2.5mediumvsGPT-5.3 Chatnone Claude Sonnet 4.6nonevsGrok 4.20medium GPT-5.3 ChatnonevsQwen3.6 Flashmedium DeepSeek V3.2mediumvsGPT-5.3 Chatnone GPT-5.3 ChatnonevsGrok Build 0.1medium DeepSeek V4 ProhighvsGPT-5.3 Chatnone Seed-2.0-MinimediumvsGPT-5.3 Chatnone GPT-5.3 ChatnonevsMiMo-V2.5-Promedium MiniMax M3mediumvsGPT-5.3 Chatnone