AI BENCHY
Advertise here
#31

Gemini 3.5 Flash Lite

Google Release: 2026-07-21 Tested on: 2026-07-21 16:29 google/gemini-3.5-flash-lite::high
~150B total (~10B active)MoEClosedEstimated
(high) (medium) (low)

Summary

Gemini 3.5 Flash Lite scores 8.1 on AI BENCHY and ranks #31. It has 10.0 reliability, a 81.8% pass rate, $0.584 total cost, and 9.48s average response time.

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

8.1

Consistency

7.5

Reliability

10.0

Total Cost (Current Price)

$0.584

Total Output Tokens

220,822

Total Input Tokens

105,138

Input Price

$0.300 / 1M

Output Price

$2.500 / 1M

Tests Correct

Wrong Tests: 8

Attempt pass rate: 81.8%

Flaky tests

7

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

Response Time (avg)

9.48s

Response Time (max): 43.93s

Response Time (total): 208.52s

Wrong answer: 6 Did not follow instructions: 1 No answer: 1

Hamster playing table tennis

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

#31 Gemini 3.5 Flash-Lite

high
Cost
$0.025
Time
36.8s
Tokens
9,964 tok

Run history

Tested on Score Reliability Tests Correct Total Cost Compare
2026-08-14 02:48 Re-test 8.8 10.0 $0.540 Compare
2026-08-02 09:19 Re-test 8.8 10.0 $0.538 Compare
2026-07-21 16:29 Initial run 8.1 10.0 $0.584 Current run

Price History

Historical pricing data for this model from OpenRouter.

Date Input Price Output Price
2026-07-21 16:32 $0.300 / 1M $2.500 / 1M

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 3.5 Flash LitehighvsGemini 3.5 FlashlowGemini 3.5 Flash LitehighvsClaude Opus 4.8mediumGemini 3.5 Flash LitehighvsSeed 2.1 TurbohighGemini 3.5 Flash LitehighvsClaude Opus 5lowGemini 3.5 Flash LitehighvsGPT-5.3-CodexmediumGemini 3.5 Flash LitehighvsGemini 3.6 FlashlowGemini 3.5 Flash LitehighvsGrok 4.5highGemini 3.5 Flash LitehighvsClaude Opus 4.7mediumGemini 3.5 Flash LitehighvsQwen3.8 MaxmediumGemini 3.5 Flash LitehighvsMuse Spark 1.2high

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 10.0 10.0
Coding 8.6 7.6
Combined 7.3 5.8
Data parsing and extraction 10.0 10.0
Domain specific 5.3 7.2
General Intelligence 5.4 2.5
Instructions following 8.5 6.8
Puzzle Solving 8.2 7.2
Tool Calling 10.0 10.0
Trivia 2.8 1.6

Compared models