Qwen3.5 Plus
Qwen vision-language model for visual reasoning, documents, and agent tasks
Shogo Agent Index
Estimated#65 of 9232.7range 21.5–44 · 11% of weight measured
Agentic coding
36
estimated
Long-horizon autonomy
37
30% measured
Knowledge-work agents
28
estimated
Computer use
23
estimated
Security & context learning
37
50% measured
Agentic benchmarks
| Benchmark | Score | Normalised | Index weight | Harness / source |
|---|---|---|---|---|
| SWE-bench Verified | est. | 8% | predicted 69 | |
| Terminal-Bench 2.0 | est. | 8% | predicted 42 | |
| DeepSWE | est. | 6% | predicted 29 | |
| FrontierSWE | est. | 5% | predicted 6 | |
| CursorBench | est. | 4% | predicted 29 | |
| GSO-Bench | est. | 4% | predicted 11 | |
| METR Time Horizons | est. | 10% | predicted 67 | |
| Vending-Bench 2 | $1 | 6% | source | |
| PostTrainBench | est. | 4% | predicted 19 | |
| APEX-Agents | est. | 8% | predicted 28 | |
| GDPval | est. | 7% | predicted 34 | |
| Remote Labor Index | est. | 5% | predicted 1 | |
| DeepResearch Bench | est. | 5% | predicted 45 | |
| OSWorld 2.0 | est. | 6% | predicted 3 | |
| OSWorld | est. | 4% | predicted 52 | |
| Cybench | est. | 5% | predicted 53 | |
| CL-bench | 19.8% | 5% | source |
Other benchmarks
| Benchmark | Category | Score | Source |
|---|---|---|---|
| Chess Puzzles | Reasoning | 9.0% | source |
| DTBench | Knowledge | 80.5% | source |
| GPQA Diamond | Reasoning | 84.8% | source |
| LMCA | Knowledge | 36.4% | source |
| OTIS Mock AIME | Math | 86.7% | source |
| SimpleQA Verified | Knowledge | 25.4% | source |
| WebDev Arena | Coding | 1399 | source |
API hosts
Live prices and uptime for every host serving Qwen3.5 Plus via OpenRouter.
| Host | Input | Output | Cache read | Agent $/M | Uptime 24h | Quant |
|---|---|---|---|---|---|---|
| Alibaba | $0.30 | $1.80 | — | $0.37 | 99.7% | — |