Intelligence Index
0132.3
> 69% OF MODELS
Qwen
Qwen3.5-122B-A10B
Updated: June 2026
The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. In terms of...
Specifications
- Context
- 262K
- Input
- $0.26/M
- Output
- $2.08/M
Capabilities
VISIONTEXTWEBCODINGTHINKINGWRITING
Similarly Priced Models
| Model | Provider | Context | Input Price | Output Price |
|---|---|---|---|---|
| Qwen3 VL 235B A22B Thinking | Qwen | 131K | $0.26/M | $2.6/M |
| Qwen Plus 0728 (thinking) | Qwen | 1M | $0.26/M | $0.78/M |
| Qwen Plus 0728 | Qwen | 1M | $0.26/M | $0.78/M |
| Qwen-Plus | Qwen | 1M | $0.26/M | $0.78/M |
| Minimax M2 | Minimax | 197K | $0.255/M | $1/M |
Performance Metrics
Coding Index
0234.7
> 70% OF MODELS
Agentic Index
0353.0
> 76% OF MODELS
Average Response Performance
- Output Speed
- 138.8 tok/s
- Time To First Token
- 2.53s
- Time To First Answer Token
- 16.93s
- End To End Response Time
- 20.53s
DATA SOURCE: Artificial Analysis