AI BENCHY Compare

Google: Gemma 4 31B vs Z.ai: GLM 5 Turbo

Last updated at: 2026-04-02

Metric	Gemma 4 31B Gemma 4 31B medium Release: 2026-04-02	GLM 5 Turbo GLM 5 Turbo medium Release: 2026-03-15

Metric	Gemma 4 31B Gemma 4 31B medium Release: 2026-04-02	GLM 5 Turbo GLM 5 Turbo medium Release: 2026-03-15
Score	8.6	8.0
Rank	#5	#19
Consistency	9.6	7.9
Tests Correct
Attempt pass rate	80.4%	76.5%
Flaky tests	1	5
Total Runs	51	51
Cost per result	0.109	1.509
Total Cost	$0.015	$0.166
Input Price	$0.140 / 1M	$1.200 / 1M
Output Price	$0.400 / 1M	$4.000 / 1M
Output Tokens	9,568	11,865
Reasoning Tokens	22,501	35,632
Response Time (avg)	21.81s	17.98s
Response Time (max)	68.92s	194.23s
Response Time (total)	327.16s	305.72s

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)	Output Tokens	Reasoning Tokens
Gemma 4 31B	10.0	10.0	100.0%	0		12.89s	962	2,046
GLM 5 Turbo	10.0	10.0	100.0%	0		4.82s	362	3,137

Combined	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Output Tokens	Reasoning Tokens
Gemma 4 31B	3.0	10.0	0.0%	0		0ms	0	0
GLM 5 Turbo	10.0	10.0	100.0%	0		13.88s	390	2,037

Data parsing and extraction	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Output Tokens	Reasoning Tokens
Gemma 4 31B	10.0	10.0	100.0%	0		21.11s	1,822	2,951
GLM 5 Turbo	10.0	10.0	100.0%	0		6.19s	577	3,632

Domain specific	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Output Tokens	Reasoning Tokens
Gemma 4 31B	7.7	10.0	66.7%	0		38.48s	4,349	8,985
GLM 5 Turbo	2.9	4.4	22.2%	2		71.07s	9,665	19,279

General Intelligence	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Output Tokens	Reasoning Tokens
Gemma 4 31B	10.0	10.0	100.0%	0		9.57s	105	888
GLM 5 Turbo	6.1	3.1	66.7%	1		10.05s	60	2,216

Instructions following	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Output Tokens	Reasoning Tokens
Gemma 4 31B	10.0	10.0	100.0%	0		12.76s	533	2,035
GLM 5 Turbo	10.0	10.0	100.0%	0		5.38s	255	2,183

Puzzle Solving	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Output Tokens	Reasoning Tokens
Gemma 4 31B	8.8	7.9	88.9%	1		27.63s	1,797	5,596
GLM 5 Turbo	7.3	5.8	55.6%	2		5.44s	315	2,702

Tool Calling	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Output Tokens	Reasoning Tokens
Gemma 4 31B	3.0	10.0	0.0%	0		0ms	0	0
GLM 5 Turbo	10.0	10.0	100.0%	0		9.84s	241	446

Quick Compare

Switch Comparison Pair

Gemini 3.1 Flash Lite PreviewlowvsGLM 5 Turbomedium Gemini 3 Flash PreviewnonevsGLM 5 Turbomedium Gemini 3.1 Flash Lite PreviewnonevsGLM 5 Turbomedium GPT-5.2 ChatnonevsGLM 5 Turbomedium GPT-5.3 ChatnonevsGLM 5 Turbomedium Gemini 3 Flash PreviewlowvsGLM 5 Turbomedium Gemma 4 31BmediumvsGPT-5.2 Chatnone Claude Sonnet 4.6nonevsGLM 5 Turbomedium Gemma 4 31BmediumvsGPT-5.3 Chatnone Qwen3.5 Plus 2026-02-15nonevsGLM 5 Turbomedium Claude Sonnet 4.6nonevsGemma 4 31Bmedium Gemma 4 31BnonevsGLM 5 Turbomedium