Navigate
AI BENCHY
Advertise here

Gemini 3 Flash Preview vs GPT-5 Nano (medium)

Gemini 3 Flash Preview leads on average score with 6.8 vs 6.1. Gemini 3 Flash Preview has the lower benchmark cost at $0.085 vs $0.114. Gemini 3 Flash Preview is faster at 2.95s vs 54.87s, with pass rates of 65.2% vs 56.1%.

Last updated at: 2026-07-28

Rank
#100
Total Output Tokens
10,710
Response Time (avg)
2.95s
Total Cost
$0.085
Rank
#143
Total Output Tokens
273,098
Response Time (avg)
54.87s
Total Cost
$0.114
Recommended model Gemini 3 Flash Preview

It has the best score here (6.8), while responding about 18.6x faster than GPT-5 Nano (medium).

Detailed comparison

Metric Gemini 3 Flash Preview Gemini 3 Flash Preview none Release: 2025-12-17 GPT-5 Nano GPT-5 Nano medium Release: 2025-08-07
Score 6.8 6.1
Rank #100 #143
Reliability 10.0 10.0
Consistency 8.9 7.0
Tests Correct
Attempt pass rate 65.2% 56.1%
Flaky tests 3 8
Total Runs 66 66
Cost per result 0.648 1.267
Total Cost $0.085 $0.114
Input Price $0.500 / 1M $0.050 / 1M
Output Price $3.000 / 1M $0.400 / 1M
Total Input Tokens 104,210 94,935
Output Tokens 10,710 12,042
Reasoning Tokens 0 261,056
Response Time (avg) 2.95s 54.87s
Response Time (max) 21.19s 227.89s
Response Time (total) 44.26s 822.99s

Model generation showcase

Hamster playing table tennis

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

#100 Gemini 3 Flash Preview

none
Cost
$0.003
Time
5.6s
Tokens
981 tok

#143 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
Gemini 3 Flash Preview 5.5 10.0 33.3% 0 1.80s 8,122 453 0
GPT-5 Nano 7.0 7.7 55.6% 1 41.62s 7,305 740 41,152

Quick Compare

Switch Comparison Pair