AI BENCHY
Advertise here
#5

Gemini 3 Flash Preview

Google Release: 2025-12-17 Tested on: 2026-04-11 01:44 google/gemini-3-flash-preview::low
(medium) (low) (none)

Summary

Gemini 3 Flash Preview scores 8.8 on AI BENCHY and ranks #5. It has N/A reliability, a 85.2% pass rate, $0.091 total cost, and 6.01s average response time.

What makes Gemini 3 Flash Preview unique: It is one of the highest-ranked models overall. Its total benchmark cost is unusually low for its score range.

Score

8.8

Consistency

9.5

Reliability

N/A

Total Cost (Current Price)

$0.091

Total Output Tokens

25,291

Total Input Tokens

0

Input Price

$0.500 / 1M

Output Price

$3.000 / 1M

Tests Correct

Wrong Tests: 3

Attempt pass rate: 85.2%

Flaky tests

1

Flaky tests had mixed outcomes across runs (at least one pass and one fail).

Response Time (avg)

6.01s

Response Time (max): 14.72s

Response Time (total): 108.12s

Wrong answer: 3

Generation showcase

Hamster playing table tennis

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

#5 Gemini 3 Flash Preview

low
Cost
$0.007
Time
12.1s
Tokens
2,289 tok

Run history

Tested on Score Reliability Tests Correct Total Cost Compare
2026-06-04 13:59 New test added 8.4 10.0 $0.111 Compare
2026-05-22 00:26 Suite changed 8.6 10.0 $0.106 Compare
2026-04-11 01:44 First recorded run 8.8 N/A $0.091 Current run

Run comparison

RunScoreConsistencyReliabilityTests CorrectFlaky testsTotal Output TokensTotal Input TokensTotal CostResponse Time (avg)
2026-04-11 01:44 · First recorded run8.89.5N/A15/18125,2910$0.0916.01s
2026-05-22 00:26 · Suite changed8.69.610.016/20129,4910$0.1065.86s
Difference+0.2-0.1-10-42000-$0.015+145ms

These two runs used different benchmark suites, so the deltas reflect both model changes and suite changes.

Charts

Choose the first model, then click a second model to open a side-by-side page.

Total Output Tokens

Score vs Total Output Tokens

Quick Compare

Gemini 3 Flash PreviewlowvsMiMo-V2.5-PromediumGemini 3 Flash PreviewlowvsDeepSeek V3.2mediumGemini 3 Flash PreviewlowvsQwen3.6 FlashmediumGemini 3 Flash PreviewlowvsGrok 4.20mediumGemini 3 Flash PreviewlowvsGemini 3.5 FlashhighGemini 3 Flash PreviewlowvsGemini 3 Flash PreviewmediumGemini 3 Flash PreviewlowvsNemotron 3 Ultra 550b A55bmediumFree AvailableGemini 3 Flash PreviewlowvsGPT-5.5low

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 10.0 10.0
Coding 10.0 10.0
Combined 3.0 10.0
Data parsing and extraction 10.0 10.0
Domain specific 5.3 7.2
General Intelligence 10.0 10.0
Instructions following 9.9 10.0
Puzzle Solving 10.0 10.0
Tool Calling 10.0 10.0

Compared models