AI BENCHY
Advertise here
#9

Gemini 3.5 Flash

Google Release: 2026-05-19 Tested on: 2026-07-16 23:01 google/gemini-3.5-flash::medium
~500B total (~20B active)MoEClosedEstimated
(high) (medium) (low) (minimal) (none)

Summary

Gemini 3.5 Flash scores 9.1 on AI BENCHY and ranks #9. It has 10.0 reliability, a 87.9% pass rate, $0.642 total cost, and 8.20s average response time.

What makes Gemini 3.5 Flash unique: It stands out most in Domain specific, where it ranks #3, while Puzzle Solving is its weakest area at #18.

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

9.1

Consistency

9.7

Reliability

10.0

Total Cost (Current Price)

$0.642

Total Output Tokens

59,602

Total Input Tokens

69,747

Input Price

$1.500 / 1M

Output Price

$9.000 / 1M

Tests Correct

Wrong Tests: 3

Attempt pass rate: 87.9%

Flaky tests

1

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

Response Time (avg)

8.20s

Response Time (max): 76.68s

Response Time (total): 180.47s

Wrong answer: 2 Did not follow instructions: 1

Hamster playing table tennis

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

#9 Gemini 3.5 Flash

medium
Cost
$0.201
Time
112.9s
Tokens
22,371 tok

Run history

Tested on Score Reliability Tests Correct Total Cost Compare
2026-08-14 02:47 Re-test 9.0 10.0 $0.665 Compare
2026-07-16 23:01 New test added 9.1 10.0 $0.642 Current run
2026-06-04 14:03 New test added 9.0 10.0 $0.582 Compare
2026-05-22 00:29 Re-test 9.0 10.0 $0.472 Compare
2026-05-19 23:35 Initial run 9.2 10.0 $0.393 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 23:01 · New test added66/66 attempts9.19.710.019/22159,60269,747$0.6428.20s
2026-05-19 23:35 · Initial run57/57 attempts9.210.010.017/19038,6300$0.3933.90s
Difference—-0.1-0.30.0+2+1+20972+69747+$0.250+4302ms

Benchmark coverage differs: 66/66 attempts (Target: 3 repeats per test) versus 57/57 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 FlashmediumvsQwen3.7 MaxmediumGemini 3.5 FlashmediumvsGPT-5.5mediumGemini 3.5 FlashmediumvsSeed 2.1 TurbolowGemini 3.5 FlashmediumvsQwen3.8 MaxmediumGemini 3.5 FlashmediumvsClaude Opus 5mediumGemini 3.5 FlashmediumvsGrok 4.5highGemini 3.5 FlashmediumvsClaude Opus 5highGemini 3.5 FlashmediumvsGPT-5.3-CodexmediumGemini 3.5 FlashmediumvsGemini 3.7 FlashlowGemini 3.5 FlashmediumvsSeed 2.1 Turbohigh

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 10.0 10.0
Coding 7.9 7.5
Combined 10.0 10.0
Data parsing and extraction 10.0 10.0
Domain specific 7.7 10.0
General Intelligence 10.0 10.0
Instructions following 9.9 10.0
Puzzle Solving 7.7 10.0
Tool Calling 10.0 10.0
Trivia 10.0 10.0

Compared models