AI BENCHY
Compare Charts
โค๏ธ Made by XCS
AD
Track all your projects in one dashboard. Get ๐Ÿ“Šstats, ๐Ÿ”ฅheatmaps and ๐Ÿ‘€recordings in one self-hosted dashboard.
uxwizz.com

#10

Gemini 3.1 Flash Lite Preview

Google ยท Release: 2026-03-03 ยท google/gemini-3.1-flash-lite-preview::none

Avg Score

7.70

Cost per result

0.116

Consistency

9.54

Total Cost

$0.011

Tests Correct

9

A test is fully passed only if every run passed for that test.

Wrong Tests

5

Attempt pass rate: 69.1%

Flaky tests

1

Response time: avg 1.24s ยท total 17.33s ยท max 3.39s

Wrong answer: 3 Did not follow instructions: 2

Top Models by Score

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

Quick Compare

Category Breakdown

Category Avg Score Consistency Tests Correct
Anti-AI Tricks 6.00 7.85 1/3
Data parsing and extraction 9.88 10.00 2/2
Domain specific 4.00 10.00 1/3
Instructions following 9.00 10.00 1/2
Puzzle Solving 10.00 10.00 3/3
Tool Calling 10.00 10.00 1/1