#22Google DeepMindOpen weights
Gemma 4 26B A4B
Google's 26B mixture-of-experts model with 3.8B active parameters per token. Scores 17 on the Artificial Analysis Intelligence Index at $0.10 per 1M input and $0.37 per 1M output tokens. Apache 2.0.
- Overall
- 41.1
- Input $/M
- $0.10
- Output $/M
- $0.37
- Context
- 262K
- Released
- Apr 2, 2026
- Updated
- Oct 3, 2026
Category scores
- Reasoning & Mathrank 2329.3
- Cost-efficiencyrank 388.3
- Open-sourcerank 1029.3
- Best small modelrank 529.3
Overall rank history
Weekly snapshots. Lower is better.
Strengths
- Cheapest small model at $0.10 per 1M input tokens
- Open weights (Apache 2.0)
- Best cost-efficiency in the small-model class (88.3)
Weaknesses
- Lowest intelligence score among the ranked small models
- Smaller 262k context window