Google
Gemini 3.5 Flash-Lite
Quality Score46.3
Value Score36.2
Reliability52.6
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
- $0.300
- Output
- $2.50
- Cached Input
- $0.030
- Cached Output
- not available
- Cost per task
- $0.097
Capability
- Intelligence
- 37.4
- Coding
- 49.3
- Agentic
- 27.2
- Omniscience
- 5.2
- Correct
- 29.5%
- Blended price
- $0.331
Answer outcomes
Correct 29.5%Incorrect 24.2%Abstained 46.3%
Artificial Analysis benchmarks
- GDPval-AA v2
- 32%
- τ³-Banking
- 18%
- Terminal-Bench v2.1
- 54%
- SciCode
- 41%
- Humanity’s Last Exam
- 19%
- GPQA Diamond
- 84%
- CritPt
- 0%
- AA-Omniscience
- 53%
- AA-LCR
- 75%
Similar models
- Gemini 3.5 Flash (medium)GoogleQuality Score 60.3Value Score 41.6
- Gemini 3.5 Flash (minimal)GoogleQuality Score 48.6Value Score 32.3
- Gemini 3.1 Pro PreviewGoogleQuality Score 64.2Value Score 42.0
- Gemma 4 31B (Reasoning)GoogleQuality Score 25.6Value Score 33.5
- Gemini 3.6 Flash (high)GoogleQuality Score 65.0Value Score 48.6
- Gemini 3.7 Flash (low)GoogleQuality Score 66.1Value Score 49.4