Qwen3 235B A22B Instruct 2507
Qwen instruction model for multilingual chat, reasoning, and tool use
Shogo Agent Index
UnrankedNot ranked yet: 0 agentic benchmarks measured, and we need at least 2 plus an overall capability score. It will be ranked as results are published.
Agentic coding
21
estimated
Long-horizon autonomy
31
estimated
Knowledge-work agents
19
estimated
Computer use
9
estimated
Security & context learning
20
estimated
Price
- Input
- $0.20/M
- Output
- $0.60/M
- Cache read
- $0.20/M
- 3:1 blend
- $0.30/M
- Agent-effective
- $0.22/M
Agent-effective = 20 input tokens per output token, 85% cache hits. Why.
Agentic benchmarks
| Benchmark | Score | Normalised | Index weight | Harness / source |
|---|---|---|---|---|
| SWE-bench Verified | est. | 8% | predicted 55 | |
| Terminal-Bench 2.0 | est. | 8% | predicted 13 | |
| DeepSWE | est. | 6% | predicted 13 | |
| FrontierSWE | est. | 5% | predicted 1 | |
| CursorBench | est. | 4% | predicted 20 | |
| GSO-Bench | est. | 4% | predicted 3 | |
| METR Time Horizons | est. | 10% | predicted 54 | |
| Vending-Bench 2 | est. | 6% | predicted 4 | |
| PostTrainBench | est. | 4% | predicted 13 | |
| APEX-Agents | est. | 8% | predicted 14 | |
| GDPval | est. | 7% | predicted 20 | |
| Remote Labor Index | est. | 5% | predicted 0 | |
| DeepResearch Bench | est. | 5% | predicted 42 | |
| OSWorld 2.0 | est. | 6% | predicted 1 | |
| OSWorld | est. | 4% | predicted 22 | |
| Cybench | est. | 5% | predicted 27 | |
| CL-bench | est. | 5% | predicted 14 |