Summary
Gemini 3 Flash Preview scores 1.8 on AI BENCHY and ranks #496. It has 10.0 reliability, a 4.4% pass rate, $0.105 total cost, and 52.45s average response time.
What makes Gemini 3 Flash Preview unique: It stands out most in Agentic, where it ranks #1, while Anti-AI Tricks is its weakest area at #14. It uses unusually many reasoning tokens, which can help explain its slower or more expensive runs.
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. Sparse MoE is documented for the family; counts are estimated.
1.8
Consistency
0.4
10.0
$0.105
Total Output Tokens
12,557
Total Input Tokens
134,050
Input Price
$0.500 / 1M
Output Price
$3.000 / 1M
Cache Read Price
$0.050 / 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.
Wrong Tests: 0
Attempt pass rate: 4.4%
Benchmark coverage: 3/69 attempts (Target: 3 repeats per test)
Flaky tests
0
Flaky tests had mixed outcomes across runs (at least one pass and one fail).
Price History
Historical pricing data for this model from OpenRouter.
| Date | Input Price | Output Price | Cache Read Price | Cache Write Price |
|---|---|---|---|---|
| 2026-10-01 18:33 | $0.500 / 1M | $3.000 / 1M | $0.050 / 1M | $0.084 / 1M |
Charts
Choose the first model, then click a second model to open a side-by-side page.
Score vs Total Cost
Response Time (avg)
Score vs Response Time (avg)
Total Output Tokens
Score vs Total Output Tokens
Quick Compare
Category Breakdown
| Category | Score | Consistency | Tests Correct |
|---|---|---|---|
| Agentic | 10.0 | 10.0 | |
| Anti-AI Tricks | 0.0 | 0.0 | |
| Coding | 0.0 | 0.0 | |
| Combined | 0.0 | 0.0 | |
| Data parsing and extraction | 0.0 | 0.0 | |
| Domain specific | 0.0 | 0.0 | |
| General Intelligence | 0.0 | 0.0 | |
| Instructions following | 0.0 | 0.0 | |
| Puzzle Solving | 0.0 | 0.0 | |
| Tool Calling | 0.0 | 0.0 | |
| Trivia | 0.0 | 0.0 |