Gemma 4 31B vs Qwen3.5-35B-A3B

Compared models

Recommended model Gemma 4 31B

It has the best score here (5.7), while costing about 6.9x less than Qwen3.5-35B-A3B.

Metric	Gemma 4 31B Gemma 4 31B none Release: 2026-04-02 Free Available	Qwen3.5-35B-A3B Qwen3.5-35B-A3B none Release: 2026-02-24

Metric	Gemma 4 31B Gemma 4 31B none Release: 2026-04-02 Free Available	Qwen3.5-35B-A3B Qwen3.5-35B-A3B none Release: 2026-02-24
Score	5.7	5.6
Rank	#258	#263
Reliability	10.0	10.0
Consistency	9.6	8.6
Attempts	69/69	69/69
Tests Correct
Attempt pass rate	42.0%	37.7%
Flaky tests	1	4
Total Runs	69	69
Cost per result	0.520	3.135
Total Cost	$0.031	$0.213
Input Price	$0.090 / 1M	$0.163 / 1M
Output Price	$0.340 / 1M	$1.300 / 1M
Cache Read Price	$0.050 / 1M	N/A
Cache Write Price	N/A	N/A
Total Input Tokens	270,970	218,886
Output Tokens	15,499	135,768
Reasoning Tokens	0	0
Response Time (avg)	7.28s	18.31s
Response Time (max)	44.73s	209.15s
Response Time (total)	152.84s	421.19s
Parameters	30.7B	35B total (3B active)
Availability	Open source	Open source

Cache prices apply to input tokens. Reads reuse cached prompts; writes store them and can cost extra. Output tokens use the output price.

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

none

none

Category:

Agentic	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Gemma 4 31B	3.9	9.6	0.0%	0		44.73s	145,267	2,182	0
Qwen3.5-35B-A3B	3.9	9.6	0.0%	0		141.22s	84,356	49,152	0

Anti-AI Tricks	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Gemma 4 31B	6.5	10.0	50.0%	0		1.85s	852	45	0
Qwen3.5-35B-A3B	3.4	7.9	16.7%	1		1.43s	696	574	0

Coding	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Gemma 4 31B	5.5	10.0	33.3%	0		11.19s	8,381	735	0
Qwen3.5-35B-A3B	5.5	10.0	33.3%	0		1.39s	7,808	571	0

Combined	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Gemma 4 31B	3.8	5.8	33.3%	1		29.95s	104,817	11,910	0
Qwen3.5-35B-A3B	3.8	5.8	33.3%	1		128.29s	107,066	84,104	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		2.25s	8,352	285	0
Qwen3.5-35B-A3B	10.0	10.0	100.0%	0		1.16s	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	5.3	10.0	33.3%	0		3.65s	878	27	0
Qwen3.5-35B-A3B	5.3	10.0	33.3%	0		507ms	798	17	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		2.09s	576	117	0
Qwen3.5-35B-A3B	6.5	3.4	66.7%	1		1.19s	522	114	0

Instructions following	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Gemma 4 31B	6.5	10.0	50.0%	0		2.84s	795	78	0
Qwen3.5-35B-A3B	6.3	10.0	50.0%	0		809ms	711	63	0

Puzzle Solving	Score	Consistency	Attempt pass rate	Flaky tests	Tests Correct	Response Time (avg)	Input Tokens	Output Tokens	Reasoning Tokens
Gemma 4 31B	6.5	10.0	33.3%	0		4.23s	828	108	0
Qwen3.5-35B-A3B	3.7	7.4	22.2%	1		1.35s	714	655	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
Qwen3.5-35B-A3B	10.0	10.0	100.0%	0		2.30s	8,211	264	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		1.25s	224	12	0
Qwen3.5-35B-A3B	3.0	10.0	0.0%	0		493ms	210	11	0

Switch Comparison Pair