Google fast model with 1M context. Good instruction following (88/100) and reasoning (85/100). Cost-effective for production workloads.
Metrics
Provider
Google
Organization that created the model
Open Source
No
Open source availability
Open Weights
No
Model weights publicly available
Context Window
1,000,000
Maximum input token capacity
Score Breakdown
code
20%84
Code generation, understanding, and debugging
math
20%82
Mathematical reasoning and problem solving
reasoning
15%85
Multi-step logical reasoning
intelligence
30%84
Overall reasoning and task completion ability
instruction following
88
Compatibility(3)
Sources(2)
Developed by
Google DeepMindBenchmark Performance
Compare Models| Dimension | Score |
|---|---|
| Intelligence | 84.0 |
| Reasoning | 85.0 |
| Math | 82.0 |
| Code | 84.0 |
| Instruction Following | 88.0 |
| Overall | 86 |
Loading chart...
Data: Epoch AI (CC-BY 4.0)