AI BENCHY
Advertise here
#42

Gemini 3.1 Flash Lite Preview

Google Release: 2026-03-03 Tested on: 2026-05-22 00:27 google/gemini-3.1-flash-lite-preview::low
~150B total (~10B active)MoEClosedEstimated
(high) (medium) (low) (none)

Summary

Gemini 3.1 Flash Lite Preview scores 7.6 on AI BENCHY and ranks #42. It has 10.0 reliability, a 65.0% pass rate, $0.025 total cost, and 3.01s average response time.

What makes Gemini 3.1 Flash Lite Preview unique: It stands out most in Puzzle Solving, where it ranks #1, while Coding is its weakest area at #18. Its total benchmark cost is unusually low for its score range. It is notably fast compared with similar models.

Identity note

Gemini 3.1 Flash Lite Preview was the preview version of Google: Gemini 3.1 Flash Lite.

Model facts

Researched on 2026-08-12

Estimated
Parameters
~150B total (~10B active)
Architecture
MoE
Availability
Closed
License
-

Best estimate from public evidence; the vendor did not disclose every value. Google does not disclose parameter counts.

Parameter source Availability source

Score

7.6

Consistency

10.0

Reliability

10.0

Total Cost (Current Price)

$0.025

Total Output Tokens

11,109

Total Input Tokens

0

Input Price

$0.250 / 1M

Output Price

$1.500 / 1M

Tests Correct

Wrong Tests: 7

Attempt pass rate: 65.0%

Flaky tests

0

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

Response Time (avg)

3.01s

Response Time (max): 11.91s

Response Time (total): 60.27s

Wrong answer: 6 Did not follow instructions: 1

Hamster playing table tennis

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

#42 Gemini 3.1 Flash Lite Preview

low
Cost
$0.002
Time
3.7s
Tokens
1,203 tok

Run history

Tested on Score Reliability Tests Correct Total Cost Compare
2026-08-14 02:44 Re-test 6.6 10.0 $0.646 Compare
2026-07-16 23:07 New test added 6.5 10.0 $0.646 Compare
2026-06-04 14:00 New test added 7.4 10.0 $0.026 Compare
2026-05-22 00:27 Suite changed 7.6 10.0 $0.025 Current run
2026-04-11 01:44 First recorded run 8.1 N/A $0.022 Compare

This run used a different benchmark suite. Keep suite changes in mind when reading historical movement.

Run comparison

RunBenchmark coverageScoreConsistencyReliabilityTests CorrectFlaky testsTotal Output TokensTotal Input TokensTotal CostResponse Time (avg)
2026-05-22 00:27 · Suite changed60/60 attempts7.610.010.013/20011,1090$0.0253.01s
2026-06-04 14:00 · New test added63/63 attempts7.410.010.013/21011,45232,715$0.0262.77s
Difference—+0.20.00.000-343-32715-$0.002+246ms

Benchmark coverage differs: 60/60 attempts (Target: 3 repeats per test) versus 63/63 attempts (Target: 3 repeats per test). Totals and repeat-sensitive metrics are not directly comparable.

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 3.1 Flash Lite PreviewlowvsQwen3.5-27BnoneGemini 3.1 Flash Lite PreviewlowvsInkling SmallmediumGemini 3.1 Flash Lite PreviewlowvsGemini 3.5 Flash LitelowGemini 3.1 Flash Lite PreviewlowvsGemini 3.1 Flash LitelowGemini 3.1 Flash Lite PreviewlowvsLongCat 2.0highGemini 3.1 Flash Lite PreviewlowvsQwen3.6 35B A3BmediumGemini 3.1 Flash Lite PreviewlowvsGemini 3.5 FlashminimalGemini 3.1 Flash Lite PreviewlowvsQwen3.5 Plus 2026-02-15noneGemini 3.1 Flash Lite PreviewlowvsLongCat 2.0lowGemini 3.1 Flash Lite PreviewlowvsQwen3.6 27Bmedium

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 8.3 10.0
Coding 6.8 10.0
Combined 3.0 10.0
Data parsing and extraction 10.0 10.0
Domain specific 5.3 10.0
General Intelligence 4.0 10.0
Instructions following 10.0 10.0
Puzzle Solving 10.0 10.0
Tool Calling 10.0 10.0
Trivia 3.0 10.0

Compared models