readable AI benchmarks (simplified)
Google
Gemma 4 12B (Reasoning)
Gemma 4 12B (Reasoning) has a Quality Score of 22.7, ranking 352nd among 572 scored models. Per 1M tokens, pricing is $0.100 input and $0.300 output. It has a 262,144 token context window. Its Reliability Score is 23.6, ranking 423rd among 574 scored models, below average (total average: 36.5).
Quality Score22.7coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Scorenot available
Factual reliability23.6
Cache Discountnot available
Model specification
- Reasoning
- reasoning
- Input modalities
- none
- Output modalities
- none
- Context window
- 262,144 tokens
- Weights
- open weights
Token prices USD per 1M tokens
- Input
- $0.100
- Output
- $0.300
- Cached Input
- not available
- Cache write
- not available
- Cost per task
- not available
Capability
- Intelligence
- 14.2
- Coding
- not available
- Agentic
- not available
- Omniscience
- -52.7
- Correct
- 15.6%
- Blended price
- not available
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 84.0%
Correct 15.6%Incorrect 68.3%Partial / not attempted 16.0%
Artificial Analysis benchmarks
- GDPval-AA v2
- 0%
- Humanity’s Last Exam
- 16%
- GPQA Diamond
- 75%
- CritPt
- 0%
- AA-Omniscience
- 24%
- AA-LCR
- 64%
Similar models
- Gemma 4 31B (Reasoning)GoogleQuality Score 24.3Value Score not available
- Gemma 4 26B A4B (Reasoning)GoogleQuality Score 25.1Value Score 22.5
- Gemini 2.5 Flash (Reasoning)GoogleQuality Score 27.6Value Score 22.1
- Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)GoogleQuality Score 19.5Value Score 18.0
- Gemini 2.5 Flash Preview (Sep '25) (Reasoning)GoogleQuality Score 27.9Value Score not available
- Gemini 2.5 Flash-Lite (Reasoning)GoogleQuality Score 20.2Value Score 18.6