AI BENCHY Compare

MoonshotAI: Kimi K3 vs OpenAI: GPT-5.2

Summary

Kimi K3 (max) leads on average score with 8.5 vs 8.4. GPT-5.2 (medium) has the lower benchmark cost at $0.548 vs $3.112. GPT-5.2 (medium) is faster at 16.88s vs 122.48s, with pass rates of 82.5% vs 71.4%.

Recommended modelGPT-5.2 (medium)Its score stays close to the best score here (8.4 vs 8.5), while costing about 5.7x less than Kimi K3 (max).

Last updated at: 2026-07-16

Metric	Kimi K3 Kimi K3 max Release: 2026-07-16	GPT-5.2 GPT-5.2 medium Release: 2025-12-11

Metric	Kimi K3 Kimi K3 max Release: 2026-07-16	GPT-5.2 GPT-5.2 medium Release: 2025-12-11
Score	8.5	8.4
Rank	#21	#28
Reliability	9.4	10.0
Consistency	9.2	8.4
Tests Correct
Attempt pass rate	82.5%	71.4%
Flaky tests	2	4
Total Runs	63	63
Cost per result	19.446	4.209
Total Cost	$3.112	$0.548
Input Price	$3.000 / 1M	$1.750 / 1M
Output Price	$15.000 / 1M	$14.000 / 1M
Total Input Tokens	34,916	33,967
Output Tokens	2,910	2,901
Reasoning Tokens	197,529	31,932
Response Time (avg)	122.48s	16.88s
Response Time (max)	766.58s	77.80s
Response Time (total)	2327.06s	236.34s

Generation showcase

Hamster playing table tennis

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

#21 MoonshotAI: Kimi K3

max

Cost: $0.281
Time: 506.9s
Tokens: 18,863 tok

#28 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

Category:

Anti-AI Tricks	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Kimi K3	10.0	10.0	100.0%	0		10.24s	1,638	496	2,629
GPT-5.2	6.5	8.0	58.3%	1		7.81s	606	567	2,002

Coding	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Kimi K3	10.0	10.0	100.0%	0		325.79s	8,061	460	84,012
GPT-5.2	10.0	10.0	100.0%	0		22.73s	7,302	511	11,912

Combined	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Kimi K3	10.0	10.0	100.0%	0		223.03s	12,792	399	20,460
GPT-5.2	10.0	10.0	100.0%	0		14.06s	11,019	291	1,757

Data parsing and extraction	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Kimi K3	7.3	5.8	83.3%	1		16.72s	7,839	354	2,606
GPT-5.2	10.0	10.0	100.0%	0		3.15s	7,140	234	420

Domain specific	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Kimi K3	5.9	7.2	55.6%	1		490.14s	794	80	83,180
GPT-5.2	5.9	7.2	55.6%	1		77.80s	473	42	10,342

General Intelligence	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Kimi K3	10.0	10.0	100.0%	0		14.91s	732	191	871
GPT-5.2	3.7	9.7	0.0%	0		4.32s	477	162	269

Instructions following	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Kimi K3	10.0	10.0	100.0%	0		7.66s	1,179	147	1,119
GPT-5.2	9.9	10.0	100.0%	0		3.12s	660	94	614

Puzzle Solving	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Kimi K3	10.0	10.0	100.0%	0		7.36s	1,416	495	1,368
GPT-5.2	7.5	7.3	77.8%	1		5.80s	642	735	924

Tool Calling	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Kimi K3	3.0	10.0	0.0%	0		0ms	0	0	0
GPT-5.2	4.7	1.6	66.7%	1		10.30s	5,453	239	469

Trivia	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Kimi K3	3.0	10.0	0.0%	0		19.67s	465	288	1,284
GPT-5.2	3.0	10.0	0.0%	0		28.18s	195	26	3,223

Quick Compare

Switch Comparison Pair

Kimi K3maxvsGPT-5 Minimedium Kimi K3maxvsGLM 5medium Kimi K3maxvsGPT-5.4medium Seed-2.0-LitemediumvsKimi K3max Kimi K3maxvsGPT-5.2 Chatnone Kimi K3maxvsStep 3.7 Flashmedium DeepSeek V4 FlashhighvsGPT-5.2medium Kimi K3maxvsGLM 5.2medium Claude Opus 4.7mediumvsKimi K3max Kimi K3maxvsGrok 4.5medium Muse Spark 1.1lowvsKimi K3max DeepSeek V4 FlashhighvsKimi K3max