AI BENCHY
Advertise here
#85

Gemini 3.1 Flash Lite

Google Release: 2026-05-08 Tested on: 2026-05-22 00:26 google/gemini-3.1-flash-lite::none
(high) (medium) (low) (minimal) (none)

Summary

Gemini 3.1 Flash Lite scores 6.6 on AI BENCHY and ranks #85. It has 10.0 reliability, a 55.0% pass rate, $0.013 total cost, and 1.09s average response time.

What makes Gemini 3.1 Flash Lite unique: It stands out most in Coding, where it ranks #3, while Domain specific is its weakest area at #10. Its total benchmark cost is unusually low for its score range. It is notably fast compared with similar models.

Identity note

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

Score

6.6

Consistency

8.5

Reliability

10.0

Total Cost (Current Price)

$0.013

Total Output Tokens

2,478

Total Input Tokens

0

Input Price

$0.250 / 1M

Output Price

$1.500 / 1M

Tests Correct

Wrong Tests: 11

Attempt pass rate: 55.0%

Flaky tests

4

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

Response Time (avg)

1.09s

Response Time (max): 2.97s

Response Time (total): 21.79s

Wrong answer: 10 Did not follow instructions: 1

Generation showcase

Hamster playing table tennis

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

#85 Gemini 3.1 Flash Lite

none
Cost
$0.001
Time
4.5s
Tokens
727 tok

Run history

Tested on Score Reliability Tests Correct Total Cost Compare
2026-06-04 13:59 New test added 6.4 10.0 $0.013 Compare
2026-05-22 00:26 Suite changed 6.6 10.0 $0.013 Current run
2026-05-08 12:01 Initial run 6.9 10.0 $0.011 Compare

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

Run comparison

RunScoreConsistencyReliabilityTests CorrectFlaky testsTotal Output TokensTotal Input TokensTotal CostResponse Time (avg)
2026-05-22 00:26 · Suite changed6.68.510.09/2042,4780$0.0131.09s
2026-06-04 13:59 · New test added6.48.610.09/2142,48436,710$0.0131.06s
Difference+0.1-0.10.000-6-36710-$0.001+25ms

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 LitenonevsGemini 3.1 Flash Lite PreviewlowGemini 3.1 Flash LitenonevsGemini 3.1 Flash Lite PreviewnoneGemini 3.1 Flash LitenonevsQwen3.6 27BmediumGemini 3.1 Flash LitenonevsGemini 3.1 Flash LitelowGemini 3.1 Flash LitenonevsStep 3.5 FlashmediumGemini 3.1 Flash LitenonevsGemini 3.5 FlashhighGemini 3.1 Flash LitenonevsGemini 3 Flash PreviewmediumGemini 3.1 Flash LitenonevsNemotron 3 Ultra 550b A55bmediumFree AvailableGemini 3.1 Flash LitenonevsGPT-5.5low

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 7.5 8.4
Coding 6.8 10.0
Combined 3.0 10.0
Data parsing and extraction 10.0 10.0
Domain specific 2.9 7.2
General Intelligence 4.0 10.0
Instructions following 10.0 10.0
Puzzle Solving 6.3 4.8
Tool Calling 10.0 10.0
Trivia 3.0 10.0

Compared models