readable AI benchmarks (simplified)
AI9Stars
G9v3-3B
G9v3-3B has a Quality Score of 32.2, ranking 253rd among 571 scored models. Per 1M tokens, pricing is $0.0000 input and $0.0000 output. It has a 131,072 token context window. Its Reliability Score is 47.8, ranking 152nd among 573 scored models, above average (total average: 36.5).
Quality Score32.2coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Scorenot available
Factual reliability47.8
Cache Discountnot available
Model specification
- Reasoning
- reasoning
- Input modalities
- none
- Output modalities
- none
- Context window
- 131,072 tokens
- Weights
- open weights
Token prices USD per 1M tokens
- Input
- $0.0000
- Output
- $0.0000
- Cached Input
- not available
- Cache write
- not available
- Cost per task
- not available
Capability
- Intelligence
- 10.8
- Coding
- not available
- Agentic
- not available
- Omniscience
- -4.4
- Correct
- 6.5%
- Blended price
- not available
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 17.4%
Correct 6.5%Incorrect 10.9%Partial / not attempted 82.6%
Artificial Analysis benchmarks
- Humanity’s Last Exam
- 4%
- GPQA Diamond
- 44%
- CritPt
- 0%
- AA-Omniscience
- 48%
- AA-LCR
- 41%
Similar models
- G9v3-39A5BAI9StarsQuality Score 42.7Value Score not available
- MiniCPM5-2BOpenBMBQuality Score 31.7Value Score not available
- DeepSeek V3.2 SpecialeDeepSeekQuality Score 31.7Value Score not available
- Nemotron 3.5 LightningNVIDIAQuality Score 30.5Value Score 28.1
- Granite 4.2 8BIBMQuality Score 29.2Value Score 27.5
- Command A+CohereQuality Score 34.1Value Score not available