DeepSeek V3.1
A large hybrid model that supports both thinking and non-thinking modes via prompt templates.
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
24
estimated
Long-horizon autonomy
34
estimated
Knowledge-work agents
21
estimated
Computer use
13
estimated
Security & context learning
24
estimated
Agentic benchmarks
| Benchmark | Score | Normalised | Index weight | Harness / source |
|---|---|---|---|---|
| SWE-bench Verified | est. | 8% | predicted 59 | |
| Terminal-Bench 2.0 | est. | 8% | predicted 20 | |
| DeepSWE | est. | 6% | predicted 16 | |
| FrontierSWE | est. | 5% | predicted 2 | |
| CursorBench | est. | 4% | predicted 22 | |
| GSO-Bench | est. | 4% | predicted 4 | |
| METR Time Horizons | est. | 10% | predicted 58 | |
| Vending-Bench 2 | est. | 6% | predicted 6 | |
| PostTrainBench | est. | 4% | predicted 14 | |
| APEX-Agents | est. | 8% | predicted 17 | |
| GDPval | est. | 7% | predicted 24 | |
| Remote Labor Index | est. | 5% | predicted 1 | |
| DeepResearch Bench | est. | 5% | predicted 43 | |
| OSWorld 2.0 | est. | 6% | predicted 1 | |
| OSWorld | est. | 4% | predicted 30 | |
| Cybench | est. | 5% | predicted 34 | |
| CL-bench | est. | 5% | predicted 15 |
Other benchmarks
| Benchmark | Category | Score | Source |
|---|---|---|---|
| DTBench | Knowledge | 82.7% | source |
| Fiction.LiveBench | Long context | 52.8% | source |
| LMCA | Knowledge | 24.3% | source |
| SimpleBench | Reasoning | 40.0% | source |
API hosts
Live prices and uptime for every host serving DeepSeek V3.1 via OpenRouter.
| Host | Input | Output | Cache read | Agent $/M | Uptime 24h | Quant |
|---|---|---|---|---|---|---|
| DeepInfra | $0.25 | $0.95 | $0.13 | $0.19 | 100.0% | fp4 |
| CoreWeave | $0.50 | $1.50 | $0.20 | $0.30 | 100.0% | fp8 |
| SiliconFlow | $0.27 | $1.00 | — | $0.30 | 99.7% | fp8 |