AI BENCHY Compare

Google: Gemma 4 31B vs OpenAI: GPT-5.6 Sol

Summary

Gemma 4 31B (medium) vs GPT-5.6 Sol benchmark comparison: The average score is effectively tied at 6.3 vs 6.3. Gemma 4 31B (medium) has the lower benchmark cost at $0.033 vs $0.225. GPT-5.6 Sol is faster at 1.66s vs 56.55s, with pass rates of 69.8% vs 57.1%.

Recommended model: GPT-5.6 Sol - It has the best score here (6.3), while responding about 34.1x faster than Gemma 4 31B (medium).

Last updated at: 2026-07-09

Metric	Gemma 4 31B Gemma 4 31B medium Release: 2026-04-02 Free Available	GPT-5.6 Sol GPT-5.6 Sol none Release: 2026-07-09

Metric	Gemma 4 31B Gemma 4 31B medium Release: 2026-04-02 Free Available	GPT-5.6 Sol GPT-5.6 Sol none Release: 2026-07-09
Score	6.3	6.3
Rank	#102	#101
Reliability	10.0	10.0
Consistency	9.4	9.0
Tests Correct
Attempt pass rate	69.8%	57.1%
Flaky tests	1	3
Total Runs	63	63
Cost per result	0.257	2.244
Total Cost	$0.033	$0.225
Input Price	$0.120 / 1M	$5.000 / 1M
Output Price	$0.350 / 1M	$30.000 / 1M
Total Input Tokens	17,957	34,218
Output Tokens	22,356	1,776
Reasoning Tokens	65,726	0
Response Time (avg)	56.55s	1.66s
Response Time (max)	437.40s	3.93s
Response Time (total)	1074.41s	34.81s

Generation showcase

Hamster playing table tennis

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

#102 Gemma 4 31B

medium

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

#101 GPT-5.6 Sol

none

Cost: $0.116
Time: 78.7s
Tokens: 3,944 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-5.6 Sol	8.3	10.0	75.0%	0		1.27s	606	154	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-5.6 Sol	5.5	10.0	33.3%	0		1.39s	7,302	390	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-5.6 Sol	3.0	10.0	0.0%	0		3.93s	11,019	300	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-5.6 Sol	10.0	10.0	100.0%	0		1.53s	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-5.6 Sol	3.6	7.2	22.2%	1		1.43s	723	54	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-5.6 Sol	6.5	3.4	66.7%	1		1.52s	477	91	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-5.6 Sol	8.5	6.8	83.3%	1		1.33s	660	84	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-5.6 Sol	7.7	10.0	66.7%	0		1.49s	642	211	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-5.6 Sol	10.0	10.0	100.0%	0		3.70s	5,454	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-5.6 Sol	3.0	10.0	0.0%	0		1.95s	195	24	0

Quick Compare

Switch Comparison Pair

Nemotron 3 SupermediumFree AvailablevsGPT-5.6 Solnone GPT-5.6 SolnonevsQwen3.5-35B-A3Bmedium Gemma 4 31BmediumFree AvailablevsGPT-5.5none Seed-2.0-LitenonevsGemma 4 31BmediumFree Available Gemini 3.1 Flash LitelowvsGPT-5.6 Solnone Gemma 4 31BmediumFree AvailablevsGPT-5.6 Lunalow Gemini 3.1 Flash Lite PreviewlowvsGPT-5.6 Solnone Gemini 3.1 Flash LiteminimalvsGPT-5.6 Solnone Gemma 4 31BmediumFree AvailablevsQwen3.5-Flashnone Gemma 4 31BmediumFree AvailablevsNemotron 3 Ultra 550b A55bnoneFree Available GPT-5.6 SolnonevsQwen3.6 27Bmedium GPT-5.6 SolnonevsStep 3.5 Flashmedium