AI BENCHY
Advertise here
#3

Gemini 3.5 Flash

Google Release: 2026-05-19 Tested on: 2026-05-22 00:28 google/gemini-3.5-flash::low
~500B total (~20B active)MoEClosedEstimated
(high) (medium) (low) (minimal) (none)

Summary

Gemini 3.5 Flash scores 9.3 on AI BENCHY and ranks #3. It has 10.0 reliability, a 90.0% pass rate, $0.285 total cost, and 2.98s average response time.

What makes Gemini 3.5 Flash unique: It stands out most in Domain specific, where it ranks #2, while Coding is its weakest area at #12. It is one of the highest-ranked models overall. Its total benchmark cost is unusually low for its score range.

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

9.3

Consistency

10.0

Reliability

10.0

Total Cost (Current Price)

$0.285

Total Output Tokens

25,965

Total Input Tokens

0

Input Price

$1.500 / 1M

Output Price

$9.000 / 1M

Tests Correct

Wrong Tests: 2

Attempt pass rate: 90.0%

Flaky tests

0

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

Response Time (avg)

2.98s

Response Time (max): 6.44s

Response Time (total): 59.59s

Wrong answer: 2

Hamster playing table tennis

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

#3 Gemini 3.5 Flash

low
Cost
$0.068
Time
39.1s
Tokens
7,588 tok

Run history

Tested on Score Reliability Tests Correct Total Cost Compare
2026-08-14 02:46 Re-test 8.8 10.0 $0.449 Compare
2026-07-16 22:57 New test added 8.9 10.0 $0.433 Compare
2026-06-04 14:02 New test added 9.4 10.0 $0.349 Compare
2026-05-22 00:28 Suite changed 9.3 10.0 $0.285 Current run
2026-05-19 23:35 Initial run 9.6 10.0 $0.245 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)
2026-05-22 00:28 · Suite changed60/60 attempts9.310.010.018/20025,9650$0.2852.98s
2026-08-14 02:46 · Re-test66/66 attempts8.89.310.018/22235,19587,826$0.4495.76s
Difference—+0.5+0.70.00-2-9230-87826-$0.164-2780ms

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

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 FlashlowvsSeed 2.1 TurbohighGemini 3.5 FlashlowvsGemini 3.5 Flash LitehighGemini 3.5 FlashlowvsGPT-5.3-CodexmediumGemini 3.5 FlashlowvsClaude Opus 4.8mediumGemini 3.5 FlashlowvsGrok 4.5highGemini 3.5 FlashlowvsClaude Opus 5lowGemini 3.5 FlashlowvsQwen3.8 MaxmediumGemini 3.5 FlashlowvsGemini 3.6 FlashlowGemini 3.5 FlashlowvsGPT-5.5mediumGemini 3.5 FlashlowvsClaude Opus 4.7medium

Category Breakdown

Category Score Consistency Tests Correct
Anti-AI Tricks 10.0 10.0
Coding 6.8 10.0
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 10.0 10.0
Tool Calling 10.0 10.0
Trivia 10.0 10.0

Compared models