Model detail
Gemini 3.6 Flash
Provider: Google · Public slug: google-gemini-3-6-flash
- Rank
- Partial average — 1/3
- Rank movement
- Baseline
- Score
- 57.5
- Last measured
- 2026-07-26
- Coverage
- Missing Intensive, Baseline
Reasoning profile
Available reasoning settings
MinimalLowMediumHigh
Checked on 2026-07-24 · provider source
Tested reasoning settings
| Provider setting | Score | Evidence | Filter bracket |
|---|---|---|---|
| Medium | 57.5 | Retained request evidence; eligible | Balanced |
| Minimal | 40.5 | Retained request evidence; eligible | Baseline |
| High | 55.4 | Retained request evidence; eligible | Intensive |
Filter assignment status
- Baseline: Minimal — tested and eligible
- Balanced: Medium — tested and eligible
- Intensive: High — tested and eligible
Generation health
Medium: 25% / 75% / 0% · n 16 Missing Intensive, BaselineHigh repair rateCost summary
- Mean standard list-price equivalent
- $0.17
- Median unique-cell cost
- $0.17
- Unique-cell range
- $0.03–$0.34
- Coverage
- 24 unique cells / 48 observed runs
- Observed-run total
- $8.32
- Evidence basis
- Provider-reported
- Mean output
- 20k tok
- Output range
- 1.9k–46k tok
- Token samples
- 48
Cost means equal-weight unique model/game/reasoning cells.
Run setup
- Overall Models: combines public reasoning variants
- Standard GameBench code-generation prompt