Google
Gemma 4 26B A4B (Non-reasoning)
Quality Score15.0
Value Score20.2
Reliability18.8
Cache Discount4%
Model specification
- Reasoning
- non-reasoning
- Input modalities
- text, image, video
- Output modalities
- text
- Context window
- 256k tokens
- Weights
- open weights
Token prices USD per 1M tokens
- Input
- $0.130
- Output
- $0.400
- Cached Input
- $0.125
- Cached Output
- not available
- Cost per task
- not available
Capability
- Intelligence
- 20.4
- Coding
- not available
- Agentic
- not available
- Omniscience
- -62.3
- Correct
- 15.5%
- Blended price
- $0.154
Answer outcomes
Correct 15.5%Incorrect 77.8%Abstained 6.7%
Artificial Analysis benchmarks
- SciCode
- 37%
- Humanity’s Last Exam
- 11%
- GPQA Diamond
- 71%
- CritPt
- 0%
- AA-Omniscience
- 19%
- AA-LCR
- 41%
Similar models
- Gemma 4 31B (Non-reasoning)GoogleQuality Score 19.8Value Score 21.9
- Gemma 4 12B (Non-reasoning)GoogleQuality Score 11.6Value Score 14.0
- Gemma 4 E4B (Non-reasoning)GoogleQuality Score 9.2Value Score 10.4
- Gemma 4 E2B (Non-reasoning)GoogleQuality Score 6.3Value Score not available
- Gemma 3 270MGoogleQuality Score 1.8Value Score not available
- Gemma 4 12B (Reasoning)GoogleQuality Score 19.1Value Score 22.3