Google
Gemma 4 12B (Reasoning)
Quality Score19.1
Value Score22.3
Reliability23.6
Cache Discountnot available
Model specification
- Reasoning
- reasoning
- Input modalities
- text, image, video, speech
- Output modalities
- text
- Context window
- 256k tokens
- Weights
- open weights
Token prices USD per 1M tokens
- Input
- $0.100
- Output
- $0.300
- Cached Input
- not available
- Cached Output
- not available
- Cost per task
- not available
Capability
- Intelligence
- 22.2
- Coding
- 31.0
- Agentic
- not available
- Omniscience
- -52.7
- Correct
- 15.6%
- Blended price
- $0.120
Answer outcomes
Correct 15.6%Incorrect 68.3%Abstained 16.0%
Artificial Analysis benchmarks
- GDPval-AA v2
- 7%
- Terminal-Bench v2.1
- 27%
- SciCode
- 38%
- Humanity’s Last Exam
- 16%
- GPQA Diamond
- 75%
- CritPt
- 0%
- AA-Omniscience
- 24%
- AA-LCR
- 62%
Similar models
- Gemma 4 26B A4B (Reasoning)GoogleQuality Score 22.7Value Score 26.4
- DiffusionGemma 26B A4BGoogleQuality Score 13.9Value Score not available
- Gemma 4 31B (Reasoning)GoogleQuality Score 25.6Value Score 33.5
- Gemma 4 E4B (Reasoning)GoogleQuality Score 13.9Value Score 13.8
- Gemma 4 E2B (Reasoning)GoogleQuality Score 10.6Value Score not available
- Gemma 4 31B (Non-reasoning)GoogleQuality Score 19.8Value Score 21.9