Navigate
AI BENCHY
Advertise here

Gemma 4 31B vs GPT-5 Nano (medium)

Gemma 4 31B leads on average score with 6.1 vs 6.0. Gemma 4 31B has the lower benchmark cost at $0.018 vs $0.118. Gemma 4 31B is faster at 5.41s vs 54.20s, with pass rates of 43.9% vs 54.5%.

Last updated at: 2026-08-15

Rank
#176
Total Output Tokens
13,317
Response Time (avg)
5.41s
Total Cost
$0.018
Rank
#184
Total Output Tokens
282,437
Response Time (avg)
54.20s
Total Cost
$0.118
Recommended model Gemma 4 31B

It has the best score here (6.1), while costing about 6.9x less than GPT-5 Nano (medium).

Detailed comparison

Metric Gemma 4 31B Gemma 4 31B none Release: 2026-04-02 Free Available GPT-5 Nano GPT-5 Nano medium Release: 2025-08-07
Score 6.1 6.0
Rank #176 #184
Reliability 10.0 10.0
Consistency 9.6 6.6
Attempts 66/66 66/66
Tests Correct
Attempt pass rate 43.9% 54.5%
Flaky tests 1 9
Total Runs 66 66
Cost per result 0.366 1.472
Total Cost $0.018 $0.118
Input Price $0.100 / 1M $0.050 / 1M
Output Price $0.340 / 1M $0.400 / 1M
Total Input Tokens 125,703 94,944
Output Tokens 13,317 12,037
Reasoning Tokens 0 270,400
Response Time (avg) 5.41s 54.20s
Response Time (max) 29.95s 227.89s
Response Time (total) 108.12s 867.23s
Parameters 30.7B ~120B total (~5B active)
Availability Open source Closed

Model generation showcase

Hamster playing table tennis

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

#176 Gemma 4 31B

none
Cost
$0.001
Time
12.8s
Tokens
795 tok

#184 GPT-5 Nano

medium
Cost
$0.006
Time
108.5s
Tokens
13,209 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

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
GPT-5 Nano 7.0 7.7 55.6% 1 41.62s 7,305 740 41,152

Quick Compare

Switch Comparison Pair