GPT-5.2 Chat vs Qwen3.8 27B (medium)

Compared models

Recommended model Qwen3.8 27B (medium)

Its score stays close to the best score here (7.8 vs 7.9), while costing about 10.4x less than GPT-5.2 Chat.

Metric	GPT-5.2 Chat GPT-5.2 Chat none Release: 2025-12-11	Qwen3.8 27B Qwen3.8 27B medium Release: 2026-08-14

Metric	GPT-5.2 Chat GPT-5.2 Chat none Release: 2025-12-11	Qwen3.8 27B Qwen3.8 27B medium Release: 2026-08-14
Score	7.9	7.8
Rank	#91	#101
Reliability	10.0	9.6
Consistency	8.6	9.7
Attempts	66/66	66/66
Tests Correct
Attempt pass rate	69.7%	66.7%
Flaky tests	4	1
Total Runs	66	66
Cost per result	4.564	~0.409
Total Cost	$0.594	~$0.058
Input Price	$1.750 / 1M	N/A
Output Price	$14.000 / 1M	N/A
Total Input Tokens	101,104	98,266
Output Tokens	29,742	1,861
Reasoning Tokens	0	134,301
Response Time (avg)	7.73s	33.05s
Response Time (max)	38.52s	214.63s
Response Time (total)	162.40s	694.04s
Parameters	~400B total (~17B active)	27.3B
Availability	Closed	Weights available

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

none

medium

Category:

Anti-AI Tricks	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
GPT-5.2 Chat	8.7	7.9	91.7%	1		3.40s	606	1,807	0
Qwen3.8 27B	10.0	10.0	100.0%	0		2.93s	672	228	1,842

Coding	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
GPT-5.2 Chat	8.8	7.8	88.9%	1		9.82s	7,305	6,731	0
Qwen3.8 27B	10.0	10.0	100.0%	0		40.50s	7,893	585	26,808

Combined	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
GPT-5.2 Chat	7.3	5.8	83.3%	1		13.91s	78,055	7,923	0
Qwen3.8 27B	8.7	6.9	83.3%	1		124.48s	77,767	70	51,705

Data parsing and extraction	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
GPT-5.2 Chat	10.0	10.0	100.0%	0		3.05s	7,140	980	0
Qwen3.8 27B	6.5	10.0	50.0%	0		8.76s	9,039	144	2,271

Domain specific	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
GPT-5.2 Chat	3.0	10.0	0.0%	0		23.67s	579	7,128	0
Qwen3.8 27B	5.3	10.0	33.3%	0		76.98s	780	12	41,184

General Intelligence	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
GPT-5.2 Chat	4.4	3.0	33.3%	1		3.20s	477	335	0
Qwen3.8 27B	5.0	10.0	0.0%	0		9.20s	516	204	1,299

Instructions following	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
GPT-5.2 Chat	9.8	10.0	100.0%	0		5.51s	660	1,441	0
Qwen3.8 27B	10.0	10.0	100.0%	0		2.54s	699	48	984

Puzzle Solving	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
GPT-5.2 Chat	7.7	10.0	66.7%	0		4.10s	642	1,603	0
Qwen3.8 27B	8.3	10.0	66.7%	0		12.62s	696	444	6,237

Tool Calling	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
GPT-5.2 Chat	10.0	10.0	100.0%	0		4.68s	5,445	555	0
Qwen3.8 27B	3.0	10.0	0.0%	0		0ms	0	0	0

Trivia	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
GPT-5.2 Chat	3.0	10.0	0.0%	0		6.89s	195	1,239	0
Qwen3.8 27B	3.0	10.0	0.0%	0		11.29s	204	126	1,971

Switch Comparison Pair