AI BENCHY Compare

Google: Gemma 4 31B vs Qwen: Qwen3.5-27B

Summary

Gemma 4 31B vs Qwen3.5-27B benchmark comparison: Gemma 4 31B leads on average score with 6.3 vs 5.9. Qwen3.5-27B has the lower benchmark cost at $0.015 vs $0.033. Qwen3.5-27B is faster at 1.68s vs 56.55s, with pass rates of 69.8% vs 38.1%.

Recommended model: Qwen3.5-27B - Its score stays close to the best score here (5.9 vs 6.3), while costing about 2.3x less than Gemma 4 31B.

Last updated at: 2026-06-12

Metric	Gemma 4 31B Gemma 4 31B medium Release: 2026-04-02 Free Available	Qwen3.5-27B Qwen3.5-27B none Release: 2026-02-24

Metric	Gemma 4 31B Gemma 4 31B medium Release: 2026-04-02 Free Available	Qwen3.5-27B Qwen3.5-27B none Release: 2026-02-24
Score	6.3	5.9
Rank	#87	#109
Reliability	10.0	10.0
Consistency	9.4	9.3
Tests Correct
Attempt pass rate	69.8%	38.1%
Flaky tests	1	2
Total Runs	63	63
Cost per result	0.257	0.249
Total Cost	$0.033	$0.015
Input Price	$0.120 / 1M	$0.195 / 1M
Output Price	$0.350 / 1M	$1.560 / 1M
Total Input Tokens	17,957	44,478
Output Tokens	22,356	3,592
Reasoning Tokens	65,726	0
Response Time (avg)	56.55s	1.68s
Response Time (max)	437.40s	9.39s
Response Time (total)	1074.41s	35.25s

Generation showcase

Hamster playing table tennis

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

#87 Gemma 4 31B

medium

Cost: $0.002
Time: 45.7s
Tokens: 2,696 tok

#109 Qwen3.5-27B

none

Cost: $0.007
Time: 42.9s
Tokens: 4,273 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
Gemma 4 31B	10.0	10.0	100.0%	0		12.89s	816	962	2,046
Qwen3.5-27B	4.8	10.0	25.0%	0		788ms	696	267	0

Coding	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Gemma 4 31B	4.3	5.8	22.2%	1		219.76s	5,568	11,098	33,212
Qwen3.5-27B	5.8	10.0	33.3%	0		1.80s	7,913	415	0

Combined	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Gemma 4 31B	3.0	10.0	0.0%	0		0ms	0	0	0
Qwen3.5-27B	2.8	1.6	33.3%	1		9.39s	16,918	1,461	0

Data parsing and extraction	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Gemma 4 31B	10.0	10.0	100.0%	0		21.11s	8,334	1,822	2,951
Qwen3.5-27B	10.0	10.0	100.0%	0		1.43s	7,794	243	0

Domain specific	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Gemma 4 31B	7.7	10.0	66.7%	0		38.48s	876	4,349	8,985
Qwen3.5-27B	3.0	10.0	0.0%	0		540ms	789	15	0

General Intelligence	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Gemma 4 31B	10.0	10.0	100.0%	0		9.57s	567	105	888
Qwen3.5-27B	5.0	10.0	0.0%	0		2.51s	522	126	0

Instructions following	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Gemma 4 31B	10.0	10.0	100.0%	0		12.76s	777	533	2,035
Qwen3.5-27B	6.3	10.0	50.0%	0		1.03s	711	69	0

Puzzle Solving	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Gemma 4 31B	9.9	10.0	100.0%	0		26.91s	801	1,795	5,595
Qwen3.5-27B	6.7	7.9	55.6%	1		1.38s	714	683	0

Tool Calling	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Gemma 4 31B	3.0	10.0	0.0%	0		0ms	0	0	0
Qwen3.5-27B	10.0	10.0	100.0%	0		3.54s	8,211	303	0

Trivia	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Gemma 4 31B	3.0	10.0	0.0%	0		90.14s	218	1,692	10,014
Qwen3.5-27B	3.0	10.0	0.0%	0		599ms	210	10	0

Quick Compare

Switch Comparison Pair