AI BENCHY Compare

Qwen: Qwen3.7 Max vs Z.ai: GLM 5.2

Summary

Qwen3.7 Max vs GLM 5.2 benchmark comparison: GLM 5.2 leads on average score with 7.1 vs 6.9. Qwen3.7 Max has the lower benchmark cost at $0.054 vs $0.076. Qwen3.7 Max is faster at 1.30s vs 6.34s, with pass rates of 66.7% vs 60.3%.

Recommended model: Qwen3.7 Max - Its score stays close to the best score here (6.9 vs 7.1), while responding about 4.9x faster than GLM 5.2.

Last updated at: 2026-06-18

Metric	Qwen3.7 Max Qwen3.7 Max none Release: 2026-05-22	GLM 5.2 GLM 5.2 none Release: 2026-06-17

Metric	Qwen3.7 Max Qwen3.7 Max none Release: 2026-05-22	GLM 5.2 GLM 5.2 none Release: 2026-06-17
Score	6.9	7.1
Rank	#68	#61
Reliability	10.0	9.9
Consistency	10.0	9.6
Tests Correct
Attempt pass rate	66.7%	60.3%
Flaky tests	0	1
Total Runs	63	63
Cost per result	0.744	0.628
Total Cost	$0.054	$0.076
Input Price	$1.250 / 1M	$1.400 / 1M
Output Price	$3.750 / 1M	$4.400 / 1M
Total Input Tokens	37,107	38,671
Output Tokens	1,994	4,817
Reasoning Tokens	0	0
Response Time (avg)	1.30s	6.34s
Response Time (max)	3.92s	20.69s
Response Time (total)	27.21s	133.19s

Generation showcase

Hamster playing table tennis

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

#68 Qwen3.7 Max

none

Cost: $0.046
Time: 195.0s
Tokens: 12,171 tok

#61 GLM 5.2

none

Invalid SVG

Cost: $0.033
Time: 87.7s
Tokens: 7,455 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

Anti-AI Tricks	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Qwen3.7 Max	6.5	10.0	50.0%	0		1.08s	696	242	0
GLM 5.2	8.3	10.0	75.0%	0		3.70s	567	313	0

Coding	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Qwen3.7 Max	5.5	10.0	33.3%	0		1.35s	7,911	582	0
GLM 5.2	3.7	9.5	0.0%	0		7.55s	7,263	1,958	0

Combined	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Qwen3.7 Max	3.0	10.0	0.0%	0		2.17s	9,549	171	0
GLM 5.2	10.0	10.0	100.0%	0		20.69s	14,296	1,489	0

Data parsing and extraction	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Qwen3.7 Max	10.0	10.0	100.0%	0		1.35s	7,794	243	0
GLM 5.2	10.0	10.0	100.0%	0		7.17s	7,113	204	0

Domain specific	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Qwen3.7 Max	7.7	10.0	66.7%	0		975ms	789	15	0
GLM 5.2	5.3	10.0	33.3%	0		6.50s	696	27	0

General Intelligence	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Qwen3.7 Max	10.0	10.0	100.0%	0		1.04s	522	120	0
GLM 5.2	6.1	3.1	66.7%	1		4.42s	480	82	0

Instructions following	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Qwen3.7 Max	10.0	10.0	100.0%	0		943ms	711	72	0
GLM 5.2	9.8	10.0	100.0%	0		3.84s	642	66	0

Puzzle Solving	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Qwen3.7 Max	10.0	10.0	100.0%	0		1.13s	714	314	0
GLM 5.2	7.7	10.0	66.7%	0		3.31s	618	265	0

Tool Calling	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Qwen3.7 Max	10.0	10.0	100.0%	0		3.92s	8,211	222	0
GLM 5.2	10.0	10.0	100.0%	0		15.76s	6,807	400	0

Trivia	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Qwen3.7 Max	3.0	10.0	0.0%	0		856ms	210	13	0
GLM 5.2	3.0	10.0	0.0%	0		3.41s	189	13	0

Quick Compare

Switch Comparison Pair

Gemini 3.5 FlashminimalvsQwen3.7 Maxnone Gemma 4 26B A4BmediumFree AvailablevsGLM 5.2none Step 3.7 FlashhighvsGLM 5.2none Ring-2.6-1TmediumvsQwen3.7 Maxnone Kimi K2.7 CodemediumvsGLM 5.2none Qwen3.7 MaxnonevsMiMo-V2.5medium Kimi K2.7 CodemediumvsQwen3.7 Maxnone gpt-oss-120bmediumFree AvailablevsQwen3.7 Maxnone GPT-5 NanomediumvsQwen3.7 Maxnone Grok 4.20mediumvsGLM 5.2none Qwen3.7 MaxnonevsGLM 5.1medium Qwen3.7 MaxnonevsStep 3.7 Flashhigh