AI BENCHY Compare

StepFun: Step 3.7 Flash vs Z.ai: GLM 5.2

Summary

Step 3.7 Flash (medium) leads on average score with 8.5 vs 8.0. Step 3.7 Flash (medium) has the lower benchmark cost at $0.376 vs $0.667. Step 3.7 Flash (medium) is faster at 20.35s vs 37.09s, with pass rates of 73.0% vs 77.8%.

Recommended modelStep 3.7 Flash (medium)It has the best score here (8.5), while costing about 1.8x less than GLM 5.2 (high).

Last updated at: 2026-07-14

Metric	Step 3.7 Flash Step 3.7 Flash medium Release: 2026-05-29	GLM 5.2 GLM 5.2 high Release: 2026-06-17

Metric	Step 3.7 Flash Step 3.7 Flash medium Release: 2026-05-29	GLM 5.2 GLM 5.2 high Release: 2026-06-17
Score	8.5	8.0
Rank	#23	#32
Reliability	9.9	9.3
Consistency	9.3	7.6
Tests Correct
Attempt pass rate	73.0%	77.8%
Flaky tests	2	6
Total Runs	61	63
Cost per result	2.686	4.255
Total Cost	$0.376	$0.667
Input Price	$0.200 / 1M	$0.929 / 1M
Output Price	$1.150 / 1M	$2.918 / 1M
Total Input Tokens	39,981	34,993
Output Tokens	319,958	51,575
Reasoning Tokens	0	166,065
Response Time (avg)	20.35s	37.09s
Response Time (max)	113.98s	180.69s
Response Time (total)	427.42s	778.91s

Generation showcase

Hamster playing table tennis

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

#23 Step 3.7 Flash

medium

Cost: $0.006
Time: 46.2s
Tokens: 4,466 tok

#32 GLM 5.2

high

Invalid SVG

Cost: $0.000
Time: 300.0s
Tokens: 0 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
Step 3.7 Flash	8.7	7.9	91.7%	1		9.65s	756	32,185	0
GLM 5.2	10.0	10.0	100.0%	0		5.80s	639	406	2,660

Coding	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Step 3.7 Flash	8.8	7.8	88.9%	1		27.42s	7,437	44,797	0
GLM 5.2	6.4	4.4	77.8%	2		73.03s	5,124	2,302	22,546

Combined	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Step 3.7 Flash	10.0	10.0	100.0%	0		9.06s	13,683	7,106	0
GLM 5.2	10.0	10.0	100.0%	0		43.51s	12,696	711	4,267

Data parsing and extraction	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Step 3.7 Flash	10.0	10.0	100.0%	0		2.75s	7,398	3,020	0
GLM 5.2	10.0	10.0	100.0%	0		5.81s	7,143	435	1,414

Domain specific	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Step 3.7 Flash	7.7	10.0	66.7%	0		48.27s	708	70,347	0
GLM 5.2	3.5	4.4	33.3%	2		73.97s	551	46,693	90,566

General Intelligence	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Step 3.7 Flash	4.0	10.0	0.0%	0		6.85s	525	3,987	0
GLM 5.2	10.0	10.0	100.0%	0		12.90s	498	63	1,743

Instructions following	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Step 3.7 Flash	9.8	10.0	100.0%	0		1.83s	735	2,166	0
GLM 5.2	10.0	10.0	100.0%	0		4.26s	678	151	1,210

Puzzle Solving	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Step 3.7 Flash	5.7	9.9	33.3%	0		6.19s	756	15,071	0
GLM 5.2	6.0	4.6	66.7%	2		33.71s	665	568	22,392

Tool Calling	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Step 3.7 Flash	10.0	10.0	100.0%	0		4.16s	7,746	2,115	0
GLM 5.2	10.0	10.0	100.0%	0		9.25s	6,861	246	503

Trivia	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Step 3.7 Flash	3.0	10.0	0.0%	0		113.98s	237	139,164	0
GLM 5.2	3.0	10.0	0.0%	0		127.82s	138	0	18,764

Quick Compare

Switch Comparison Pair

GPT-5.2 ChatnonevsStep 3.7 Flashmedium GPT-5.4 MinimediumvsGLM 5.2high Qwen3.5 Plus 2026-02-15mediumvsGLM 5.2high KAT-Coder-Pro V2.5lowvsGLM 5.2high Nemotron 3 Ultra 550b A55bmediumFree AvailablevsGLM 5.2high Qwen3.7 PlusmediumvsGLM 5.2high Qwen3.5-27BmediumvsGLM 5.2high Claude Sonnet 5mediumvsGLM 5.2high Qwen3.6 PlusmediumvsGLM 5.2high Gemini 2.5 FlashmediumvsGLM 5.2high GPT-5.6 TerramediumvsGLM 5.2high Claude Sonnet 4.6mediumvsGLM 5.2high