Google
Gemini 3.5 Flash (medium)
Quality Score60.3
Value Score41.6
Reliability60.4
Cache Discount90%
Model specification
- Reasoning
- reasoning
- Input modalities
- text, image, video, speech
- Output modalities
- text
- Context window
- 1M tokens
- Weights
- closed weights
Token prices USD per 1M tokens
- Input
- $1.50
- Output
- $9.00
- Cached Input
- $0.150
- Cached Output
- not available
- Cost per task
- not available
Capability
- Intelligence
- 46.7
- Coding
- not available
- Agentic
- not available
- Omniscience
- 20.8
- Correct
- 51.0%
- Blended price
- $1.31
Answer outcomes
Correct 51.0%Incorrect 30.2%Abstained 18.7%
Artificial Analysis benchmarks
- SciCode
- 53%
- Humanity’s Last Exam
- 41%
- GPQA Diamond
- 92%
- CritPt
- 11%
- AA-Omniscience
- 60%
- AA-LCR
- 80%
Similar models
- Gemini 3.1 Pro PreviewGoogleQuality Score 64.2Value Score 42.0
- Gemini 3.6 Flash (high)GoogleQuality Score 65.0Value Score 48.6
- Gemini 3.7 Flash (low)GoogleQuality Score 66.1Value Score 49.4
- Gemini 3.7 Flash (medium)GoogleQuality Score 68.0Value Score 51.3
- Gemini 3.7 Flash (high)GoogleQuality Score 70.3Value Score 53.5
- Gemini 3.5 Flash-LiteGoogleQuality Score 46.3Value Score 36.2