#28 Gemini 3.6 Flash
low- Cost
- $0.045
- Time
- 25.0s
- Tokens
- 6,054 tok
Google
Release: 2026-07-21
Tested on: 2026-08-14 02:49
google/gemini-3.6-flash::low
~500B total (~20B active)MoEClosedEstimated
Summary
Gemini 3.6 Flash scores 8.7 on AI BENCHY and ranks #28. It has 10.0 reliability, a 89.4% pass rate, $0.251 total cost, and 4.92s average response time.
What makes Gemini 3.6 Flash unique: It stands out most in Trivia, where it ranks #1, while Combined is its weakest area at #15. Its total benchmark cost is unusually low for its score range. It is notably fast compared with similar models.
Model facts
Researched on 2026-08-12
- 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.
8.7
Consistency
8.9
10.0
Total Output Tokens
49,721
Total Input Tokens
85,886
Input Price
$0.750 / 1M
Output Price
$3.750 / 1M
Flaky tests
3
Flaky tests had mixed outcomes across runs (at least one pass and one fail).
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
Run history
| Tested on | Score | Reliability | Tests Correct | Total Cost | Compare |
|---|---|---|---|---|---|
| 2026-08-14 02:49 Re-test | 8.7 | 10.0 | $0.251 ↓ | Current run | |
| 2026-08-02 09:19 Re-test | 8.7 | 10.0 | $0.501 | Compare | |
| 2026-07-21 16:29 Initial run | 9.4 | 10.0 | $0.517 | Compare |
This run used a different benchmark suite. Keep suite changes in mind when reading historical movement.
Run comparison
| Run | Benchmark coverage | Score | Consistency | Reliability | Tests Correct | Flaky tests | Total Output Tokens | Total Input Tokens | Total Cost | Response Time (avg) |
|---|---|---|---|---|---|---|---|---|---|---|
| 2026-08-14 02:49 · Current run | 66/66 attempts | 8.7 | 8.9 | 10.0 | 18/22 | 3 | 49,721 | 85,886 | $0.251 | 4.92s |
| 2026-07-21 16:29 · Initial run | 66/66 attempts | 9.4 | 9.6 | 10.0 | 21/22 | 1 | 52,362 | 82,715 | $0.517 | 4.42s |
| Difference | — | -0.7 | -0.7 | 0.0 | -3 | +2 | -2641 | +3171 | -$0.266 | +507ms |
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 |
|---|---|---|
| 2026-08-01 13:51 | $1.500 / 1M | $7.500 / 1M |
| 2026-08-14 12:51 | $0.750 / 1M | $3.750 / 1M |
Charts
Choose the first model, then click a second model to open a side-by-side page.
Top Models by Score
Score vs Total Cost
Response Time (avg)
Score vs Response Time (avg)
Total Output Tokens
Score vs Total Output Tokens
Quick Compare
Gemini 3.6 FlashlowvsClaude Opus 5lowGemini 3.6 FlashlowvsClaude Opus 4.7mediumGemini 3.6 FlashlowvsClaude Opus 4.8mediumGemini 3.6 FlashlowvsMuse Spark 1.2highGemini 3.6 FlashlowvsGemini 3.5 Flash LitehighGemini 3.6 FlashlowvsMuse Spark 1.2mediumGemini 3.6 FlashlowvsGemini 3.5 FlashlowGemini 3.6 FlashlowvsMuse Spark 1.1mediumGemini 3.6 FlashlowvsSeed 2.1 TurbohighGemini 3.6 FlashlowvsClaude Fable 5medium
Category Breakdown
| Category | Score | Consistency | Tests Correct |
|---|---|---|---|
| Anti-AI Tricks | 8.7 | 7.9 | |
| Coding | 7.8 | 10.0 | |
| Combined | 7.3 | 5.8 | |
| Data parsing and extraction | 10.0 | 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 | 10.0 | 10.0 | |
| Trivia | 10.0 | 10.0 |