readable AI benchmarks (simplified)
Google
Gemini 3 Flash Preview (Reasoning)
Gemini 3 Flash Preview (Reasoning) has a Quality Score of 47.8, ranking 106th among 551 scored models. Per 1M tokens, pricing is $0.500 input, $3.00 output, and $0.050 cached input. It has a 1M token context window. Its Reliability Score is 55.1, ranking 78th among 553 scored models, above average (total average: 35.6). Its Value Score is 37.0, high compared with the total Value average of 30.7.
Quality Score47.8coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score37.0
Factual reliability55.1
Cache Discount90%
Model specification
- Reasoning
- reasoning
- Input modalities
- none
- Output modalities
- none
- Context window
- 1M tokens
- Weights
- closed weights
Token prices USD per 1M tokens
- Input
- $0.500
- Output
- $3.00
- Cached Input
- $0.050
- Cache write
- not available
- Cost per task
- not available
Capability
- Intelligence
- 26.3
- Coding
- not available
- Agentic
- not available
- Omniscience
- 10.1
- Correct
- 53.4%
- Blended price
- $0.435
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 96.7%
Correct 53.4%Incorrect 43.3%Partial / not attempted 3.3%
Artificial Analysis benchmarks
- τ³-Banking
- 21%
- Humanity’s Last Exam
- 37%
- GPQA Diamond
- 90%
- CritPt
- 9%
- AA-Omniscience
- 55%
- AA-LCR
- 78%
Similar models
- Gemini 3 Pro Preview (high)GoogleQuality Score 50.3Value Score 32.9
- Gemini 3.5 Flash-LiteGoogleQuality Score 43.4Value Score 34.6
- Gemini 3 Pro Preview (low)GoogleQuality Score 42.6Value Score 27.9
- Gemini 3.1 Pro PreviewGoogleQuality Score 55.8Value Score 36.5
- Gemini 3.5 Flash (high)GoogleQuality Score 55.4Value Score 37.5
- Gemini 3.8 Flash (low)GoogleQuality Score 56.1Value Score 41.9