Thinking Machines: Inkling vs Z.ai: GLM 5.2

Inkling (high) leads on average score with 8.0 vs 7.8. GLM 5.2 (medium) has the lower benchmark cost at $0.068 vs $1.006. GLM 5.2 (medium) is faster at 23.28s vs 64.16s, with pass rates of 77.3% vs 80.3%.

Recommended modelGLM 5.2 (medium)Its score stays close to the best score here (7.8 vs 8.0), while costing about 14.9x less than Inkling (high).

Last updated at: 2026-07-18

Metric	Inkling Inkling high Release: 2026-07-18	GLM 5.2 GLM 5.2 medium Release: 2026-06-17

Metric	Inkling Inkling high Release: 2026-07-18	GLM 5.2 GLM 5.2 medium Release: 2026-06-17
Score	8.0	7.8
Rank	#28	#38
Reliability	9.8	9.5
Consistency	8.9	8.0
Tests Correct
Attempt pass rate	77.3%	80.3%
Flaky tests	3	4
Total Runs	66	63
Cost per result	6.704	2.159
Total Cost	$1.006	$0.068
Input Price	$1.000 / 1M	$0.293 / 1M
Output Price	$4.050 / 1M	$0.920 / 1M
Total Input Tokens	86,746	37,199
Output Tokens	6,055	12,261
Reasoning Tokens	220,791	49,500
Response Time (avg)	64.16s	23.28s
Response Time (max)	327.51s	101.36s
Response Time (total)	1411.59s	488.94s

Hamster playing table tennis

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

#28 Thinking Machines: Inkling

high

Cost: $0.005
Time: 32.2s
Tokens: 1,275 tok

#38 GLM 5.2

medium

Cost: $0.041
Time: 195.8s
Tokens: 9,287 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
Inkling	10.0	10.0	100.0%	0		12.68s	702	455	7,204
GLM 5.2	10.0	10.0	100.0%	0		5.89s	639	497	2,634

Coding	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Inkling	8.5	10.0	66.7%	0		148.36s	7,374	430	78,982
GLM 5.2	8.2	7.2	88.9%	1		40.96s	7,317	1,475	17,123

Combined	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Inkling	7.3	5.8	83.3%	1		63.78s	61,296	3,854	19,895
GLM 5.2	5.0	5.0	50.0%	0		51.96s	12,696	458	4,531

Data parsing and extraction	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Inkling	10.0	10.0	100.0%	0		8.19s	7,068	216	2,349
GLM 5.2	10.0	10.0	100.0%	0		13.44s	7,149	348	2,345

Domain specific	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Inkling	7.7	10.0	66.7%	0		186.39s	683	59	76,777
GLM 5.2	4.1	4.4	44.5%	2		45.47s	551	8,188	11,606

General Intelligence	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Inkling	10.0	10.0	100.0%	0		6.53s	501	182	1,151
GLM 5.2	10.0	10.0	100.0%	0		17.39s	498	54	1,842

Instructions following	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Inkling	9.8	10.0	100.0%	0		7.00s	708	93	2,098
GLM 5.2	9.9	10.0	100.0%	0		7.90s	678	94	1,518

Puzzle Solving	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Inkling	6.9	4.9	77.8%	2		10.69s	714	429	4,623
GLM 5.2	8.2	7.2	88.9%	1		13.13s	672	536	4,822

Tool Calling	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Inkling	3.0	10.0	0.0%	0		6.52s	7,481	307	601
GLM 5.2	10.0	10.0	100.0%	0		20.41s	6,861	230	550

Trivia	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Inkling	3.0	10.0	0.0%	0		153.57s	219	30	27,111
GLM 5.2	3.0	10.0	0.0%	0		34.25s	138	381	2,529

Quick Compare

Switch Comparison Pair

Step 3.7 FlashmediumvsInklinghigh GPT-5.2 ChatnonevsInklinghigh GPT-5 MinimediumvsInklinghigh Claude Opus 4.8lowvsGLM 5.2medium Kimi K3maxvsInklinghigh GPT-5.6 TerrahighvsGLM 5.2medium Kimi K3maxvsGLM 5.2medium GPT-5.6 LunahighvsGLM 5.2medium Seed-2.0-LitemediumvsInklinghigh DeepSeek V4 FlashhighvsGLM 5.2medium Qwen3.7 PlusmediumvsInklinghigh DeepSeek V4 ProhighvsGLM 5.2medium