Intelligence Index
0129.4
> 57% OF MODELS
Google
Gemma 4 31B
Updated: August 2026
Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...
Specifications
- Context
- 262K
- Input
- $0.1/M
- Output
- $0.34/M
Capabilities
VISIONTEXTWEBCODINGTHINKINGWRITING
Similarly Priced Models
| Model | Provider | Context | Input Price | Output Price |
|---|---|---|---|---|
| GPT-5.6 Luna Pro | OpenAI | 1M | $0.1/M | $0.6/M |
| GPT-5.6 Luna | OpenAI | 1M | $0.1/M | $0.6/M |
| Qwen3.5-9B | Qwen | 262K | $0.1/M | $0.15/M |
| ByteDance Seed: Seed-2.0-Mini | ByteDance | 262K | $0.1/M | $0.4/M |
| Qwen3.5 Flash | Qwen | 1M | $0.1/M | $0.4/M |
Performance Metrics
Coding Index
0243.4
> 54% OF MODELS
Agentic Index
0314.4
> 43% OF MODELS
Average Response Performance
- Output Speed
- 35.2 tok/s
- Time To First Token
- 1.09s
- Time To First Answer Token
- 50.36s
- End To End Response Time
- 64.55s
DATA SOURCE: Artificial Analysis