Qwen3.5 9B
Qwen instruction model for multilingual chat, reasoning, and tool use
Shogo Agent Index
UnrankedNot ranked yet: 1 agentic benchmark measured, and we need at least 2 plus an overall capability score. It will be ranked as results are published.
Agentic coding
21
23% measured
Long-horizon autonomy
32
estimated
Knowledge-work agents
20
estimated
Computer use
11
estimated
Security & context learning
22
estimated
Agentic benchmarks
| Benchmark | Score | Normalised | Index weight | Harness / source |
|---|---|---|---|---|
| SWE-bench Verified | est. | 8% | predicted 57 | |
| Terminal-Bench 2.0 | 9.2% | 8% | little-coder | |
| DeepSWE | est. | 6% | predicted 15 | |
| FrontierSWE | est. | 5% | predicted 2 | |
| CursorBench | est. | 4% | predicted 21 | |
| GSO-Bench | est. | 4% | predicted 4 | |
| METR Time Horizons | est. | 10% | predicted 56 | |
| Vending-Bench 2 | est. | 6% | predicted 5 | |
| PostTrainBench | est. | 4% | predicted 13 | |
| APEX-Agents | est. | 8% | predicted 16 | |
| GDPval | est. | 7% | predicted 22 | |
| Remote Labor Index | est. | 5% | predicted 1 | |
| DeepResearch Bench | est. | 5% | predicted 43 | |
| OSWorld 2.0 | est. | 6% | predicted 1 | |
| OSWorld | est. | 4% | predicted 26 | |
| Cybench | est. | 5% | predicted 30 | |
| CL-bench | est. | 5% | predicted 14 |
Other benchmarks
API hosts
Live prices and uptime for every host serving Qwen3.5 9B via OpenRouter.
| Host | Input | Output | Cache read | Agent $/M | Uptime 24h | Quant |
|---|---|---|---|---|---|---|
| Darkbloom | $0.080 | $0.13 | $0.040 | $0.050 | 100.0% | fp4 |
| DeepInfra | $0.080 | $0.12 | — | $0.080 | 100.0% | bf16 |
| DeepInfra | $0.10 | $0.15 | — | $0.10 | 99.3% | bf16 |
| SiliconFlow | $0.10 | $0.15 | — | $0.10 | 99.4% | fp8 |
| Parasail | $0.10 | $0.25 | — | $0.11 | 100.0% | bf16 |
| DeepInfra | $0.15 | $0.23 | — | $0.15 | 98.9% | bf16 |
| PrimeIntellect | $0.17 | $0.25 | $0.15 | $0.16 | 100.0% | bf16 |
| Together | $0.17 | $0.25 | — | $0.17 | 99.6% | — |