Gemma 4 31B (medium) vs Qwen3.5-35B-A3B (medium)

Compared models

Recommended model Gemma 4 31B (medium)

It has the best score here (6.2), while costing about 11.8x less than Qwen3.5-35B-A3B (medium).

Metric	Gemma 4 31B Gemma 4 31B medium Release: 2026-04-02 Free Available	Qwen3.5-35B-A3B Qwen3.5-35B-A3B medium Release: 2026-02-24

Metric	Gemma 4 31B Gemma 4 31B medium Release: 2026-04-02 Free Available	Qwen3.5-35B-A3B Qwen3.5-35B-A3B medium Release: 2026-02-24
Score	6.2	6.1
Rank	#194	#198
Reliability	10.0	10.0
Consistency	8.7	7.6
Attempts	66/66	66/66
Tests Correct
Attempt pass rate	65.2%	65.2%
Flaky tests	3	6
Total Runs	66	66
Cost per result	1.152	9.806
Total Cost	$0.100	$1.172
Input Price	$0.090 / 1M	$0.163 / 1M
Output Price	$0.340 / 1M	$1.300 / 1M
Total Input Tokens	94,969	130,450
Output Tokens	34,399	54,857
Reasoning Tokens	233,022	838,606
Response Time (avg)	78.59s	110.84s
Response Time (max)	437.40s	950.25s
Response Time (total)	1571.84s	2438.58s
Parameters	30.7B	35B total (3B active)
Availability	Open source	Open source

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

medium

medium

Category:

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
Qwen3.5-35B-A3B	10.0	10.0	100.0%	0		21.13s	672	798	42,652

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
Qwen3.5-35B-A3B	5.9	9.3	33.3%	0		206.65s	4,106	23,844	111,462

Combined	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Gemma 4 31B	2.9	5.8	16.7%	1		433.11s	77,035	12,112	157,552
Qwen3.5-35B-A3B	3.8	5.8	33.3%	1		512.79s	109,184	775	444,948

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
Qwen3.5-35B-A3B	7.3	5.9	83.3%	1		59.33s	6,061	235	19,493

Domain specific	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Gemma 4 31B	5.3	7.2	44.4%	1		59.92s	853	4,280	18,729
Qwen3.5-35B-A3B	3.5	4.4	33.3%	2		76.44s	562	14,268	98,934

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
Qwen3.5-35B-A3B	2.8	1.6	33.3%	1		30.30s	172	20	3,753

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
Qwen3.5-35B-A3B	10.0	10.0	100.0%	0		24.45s	699	97	17,361

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
Qwen3.5-35B-A3B	8.2	7.2	88.9%	1		33.13s	597	3,592	26,585

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
Qwen3.5-35B-A3B	10.0	10.0	100.0%	0		4.65s	8,193	309	1,365

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
Qwen3.5-35B-A3B	3.0	10.0	0.0%	0		177.35s	204	10,919	72,053

Switch Comparison Pair