Advertise here
#101

Gemini 3.5 Flash

Google Release: 2026-05-19 Tested on: 2026-10-01 09:22 google/gemini-3.5-flash::medium
~500B total (~20B active)MoEClosedEstimated
(high) (medium) (low) (minimal) (none)

Summary

Gemini 3.5 Flash scores 7.9 on AI BENCHY and ranks #101. It has 10.0 reliability, a 81.2% pass rate, $1.316 total cost, and 11.78s average response time.

What makes Gemini 3.5 Flash unique: It stands out most in Trivia, where it ranks #1, while Agentic is its weakest area at #16.

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

7.9

Consistency

9.3

Reliability

10.0

Total Cost (Current Price)

$1.316

Total Output Tokens

96,655

Total Input Tokens

296,760

Input Price

$1.500 / 1M

Output Price

$9.000 / 1M

Cache Read Price

$0.150 / 1M

Cache Write Price

$0.084 / 1M

Cache prices apply to input tokens. Reads reuse cached prompts; writes store them and can cost extra. Output tokens use the output price.

Tests Correct

Wrong Tests: 5

Attempt pass rate: 81.2%

Flaky tests

2

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

Response Time (avg)

11.78s

Response Time (max): 84.47s

Response Time (total): 271.03s

Wrong answer: 3 Did not follow instructions: 1 Invalid tool call: 1

Hamster playing table tennis

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

#101 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
2026-10-01 09:22 Re-test 7.9 10.0 $1.316 Current run
2026-07-16 23:01 New test added 9.1 10.0 $0.642 Compare
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)
2026-10-01 09:22 · Current run69/69 attempts7.99.310.018/23296,655296,760$1.31611.78s
2026-05-19 23:35 · Initial run57/57 attempts9.210.010.017/19038,6300$0.3933.90s
Difference—-1.4-0.70.0+1+2+58025+296760+$0.924+7883ms

Benchmark coverage differs: 69/69 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 Cache Read Price Cache Write Price
2026-08-14 12:51 $1.500 / 1M $9.000 / 1M N/A N/A
2026-10-01 18:33 $1.500 / 1M $9.000 / 1M $0.150 / 1M $0.084 / 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 MaxnoneGemini 3.5 FlashmediumvsQwen3.8 2.4T A95BhighGemini 3.5 FlashmediumvsGPT-5.4 MinimediumGemini 3.5 FlashmediumvsMiMo-V2.6-FlashmediumGemini 3.5 FlashmediumvsClaude Fable 5.1highGemini 3.5 FlashmediumvsGrok 4.5mediumGemini 3.5 FlashmediumvsGLM 5.3 FlashXmaxGemini 3.5 FlashmediumvsGLM 5.3highGemini 3.5 FlashmediumvsQwen3.5-27BmediumGemini 3.5 FlashmediumvsStep 3.7 Flashmedium

Category Breakdown

Category Score Consistency Tests Correct
Agentic 2.8 1.6
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 5.3 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