AI BENCHY
Advertise here
#75

Gemini 3.5 Flash

Google Release: 2026-05-19 Tested on: 2026-07-16 22:53 google/gemini-3.5-flash::none
~500B total (~20B active)MoEClosedEstimated
(high) (medium) (low) (minimal) (none)

Summary

Gemini 3.5 Flash scores 7.0 on AI BENCHY and ranks #75. It has 10.0 reliability, a 74.2% pass rate, $1.079 total cost, and 9.93s average response time.

What makes Gemini 3.5 Flash unique: It stands out most in Domain specific, where it ranks #1, while Combined is its weakest area at #17.

Model facts

Researched on 2026-08-12

Estimated
Parameters
~500B total (~20B 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

7.0

Consistency

8.9

Reliability

10.0

Total Cost (Current Price)

$1.079

Total Output Tokens

117,518

Total Input Tokens

13,843

Input Price

$1.500 / 1M

Output Price

$9.000 / 1M

Tests Correct

Wrong Tests: 7

Attempt pass rate: 74.2%

Flaky tests

3

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

Response Time (avg)

9.93s

Response Time (max): 64.36s

Response Time (total): 178.68s

API error: 4 Wrong answer: 3

Hamster playing table tennis

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

#75 Gemini 3.5 Flash

none
Cost
$0.225
Time
125.5s
Tokens
25,004 tok

Run history

Tested on Score Reliability Tests Correct Total Cost Compare
2026-08-14 02:46 Re-test 6.9 10.0 $1.093 Compare
2026-07-16 22:53 New test added 7.0 10.0 $1.079 Current run
2026-06-04 14:02 New test added 8.1 10.0 $1.079 Compare
2026-05-22 00:29 Suite changed 8.9 10.0 $0.924 Compare
2026-05-19 23:35 Initial run 9.1 10.0 $0.489 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)
2026-07-16 22:53 · New test added66/66 attempts7.08.910.015/223117,51813,843$1.0799.93s
2026-05-22 00:29 · Suite changed60/60 attempts8.98.610.014/173100,7600$0.9249.05s
Difference—-1.9+0.30.0-20+16758+13843+$0.156+876ms

Benchmark coverage differs: 66/66 attempts (Target: 3 repeats per test) versus 60/60 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.

Price History

Historical pricing data for this model from OpenRouter.

Date Input Price Output Price
2026-06-04 15:40 $1.500 / 1M $9.000 / 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 FlashnonevsSeed-2.0-CodehighGemini 3.5 FlashnonevsQwen3.6 FlashmediumGemini 3.5 FlashnonevsQwen3.7 FlashmediumGemini 3.5 FlashnonevsStep 3.7 FlashhighGemini 3.5 FlashnonevsKAT-Coder-Pro V2.5mediumGemini 3.5 FlashnonevsSeed-2.0-CodemediumGemini 3.5 FlashnonevsKimi K2.5mediumGemini 3.5 FlashnonevsSolar Pro 4lowGemini 3.5 FlashnonevsSeed-2.0-MinimediumGemini 3.5 FlashnonevsSolar Pro 4medium

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 10.0 10.0
Coding 8.8 7.8
Combined 3.0 10.0
Data parsing and extraction 6.5 10.0
Domain specific 7.6 7.2
General Intelligence 10.0 10.0
Instructions following 9.8 10.0
Puzzle Solving 10.0 10.0
Tool Calling 3.0 10.0
Trivia 2.8 1.6

Compared models