AI BENCHY Compare

Google: Gemma 4 31B vs OpenAI: GPT-5.4

Summary

Gemma 4 31B vs GPT-5.4 benchmark comparison: Gemma 4 31B leads on average score with 6.3 vs 5.8. Gemma 4 31B has the lower benchmark cost at $0.033 vs $0.122. GPT-5.4 is faster at 1.42s vs 56.55s, with pass rates of 69.8% vs 36.5%.

Recommended model: Gemma 4 31B - It has the best score here (6.3), while costing about 3.7x less than GPT-5.4.

Last updated at: 2026-06-12

Metric	Gemma 4 31B Gemma 4 31B medium Release: 2026-04-02 Free Available	GPT-5.4 GPT-5.4 none Release: 2026-03-05

Metric	Gemma 4 31B Gemma 4 31B medium Release: 2026-04-02 Free Available	GPT-5.4 GPT-5.4 none Release: 2026-03-05
Score	6.3	5.8
Rank	#87	#116
Reliability	10.0	10.0
Consistency	9.4	9.2
Tests Correct
Attempt pass rate	69.8%	36.5%
Flaky tests	1	2
Total Runs	63	63
Cost per result	0.257	1.740
Total Cost	$0.033	$0.122
Input Price	$0.120 / 1M	$2.500 / 1M
Output Price	$0.350 / 1M	$15.000 / 1M
Total Input Tokens	17,957	34,212
Output Tokens	22,356	2,417
Reasoning Tokens	65,726	0
Response Time (avg)	56.55s	1.42s
Response Time (max)	437.40s	2.95s
Response Time (total)	1074.41s	29.87s

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

#116 GPT-5.4

none

Cost: $0.026
Time: 18.1s
Tokens: 1,792 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
GPT-5.4	3.2	8.0	8.3%	1		1.21s	606	406	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
GPT-5.4	5.5	10.0	33.3%	0		1.62s	7,305	516	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
GPT-5.4	3.0	10.0	0.0%	0		2.89s	11,019	291	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
GPT-5.4	10.0	10.0	100.0%	0		1.04s	7,140	222	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
GPT-5.4	5.3	7.2	44.4%	1		1.07s	723	50	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
GPT-5.4	4.4	9.9	0.0%	0		1.78s	477	184	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
GPT-5.4	6.5	10.0	50.0%	0		1.07s	660	81	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
GPT-5.4	5.6	9.8	33.3%	0		1.44s	642	381	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
GPT-5.4	10.0	10.0	100.0%	0		2.75s	5,445	246	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
GPT-5.4	3.0	10.0	0.0%	0		990ms	195	40	0

Quick Compare

Switch Comparison Pair