DeepSeek V3.2
Hybrid-reasoning DeepSeek model with thinking and non-thinking modes, sparse attention, and tool-use
Shogo Agent Index
Supported#72 of 9230.0range 22.1–37.8 · 27% of weight measured
Agentic coding
32
23% measured
Long-horizon autonomy
41
30% measured
Knowledge-work agents
24
32% measured
Computer use
18
estimated
Security & context learning
29
50% measured
Agentic benchmarks
| Benchmark | Score | Normalised | Index weight | Harness / source |
|---|---|---|---|---|
| SWE-bench Verified | est. | 8% | predicted 64 | |
| Terminal-Bench 2.0 | 39.6% | 8% | Terminus 2 | |
| DeepSWE | est. | 6% | predicted 23 | |
| FrontierSWE | est. | 5% | predicted 4 | |
| CursorBench | est. | 4% | predicted 26 | |
| GSO-Bench | est. | 4% | predicted 7 | |
| METR Time Horizons | est. | 10% | predicted 63 | |
| Vending-Bench 2 | $1,034 | 6% | source | |
| PostTrainBench | est. | 4% | predicted 17 | |
| APEX-Agents | 21.3% | 8% | source | |
| GDPval | est. | 7% | predicted 29 | |
| Remote Labor Index | est. | 5% | predicted 1 | |
| DeepResearch Bench | est. | 5% | predicted 44 | |
| OSWorld 2.0 | est. | 6% | predicted 2 | |
| OSWorld | est. | 4% | predicted 42 | |
| Cybench | est. | 5% | predicted 44 | |
| CL-bench | 13.2% | 5% | source |
Other benchmarks
| Benchmark | Category | Score | Source |
|---|---|---|---|
| Aider Polyglot | Coding | 74.2% | source |
| ARC-AGI | Reasoning | 57.0% | source |
| ARC-AGI-2 | Reasoning | 4.0% | source |
| CritPt | Reasoning | 2.9% | source |
| DTBench | Knowledge | 87.7% | source |
| Fiction.LiveBench | Long context | 83.3% | source |
| GPQA Diamond | Reasoning | 83.4% | source |
| LMCA | Knowledge | 29.1% | source |
| OTIS Mock AIME | Math | 87.8% | source |
| ProofBench | Math | 8.0% | source |
| SciCode | Coding | 38.9% | source |
| TheAgentCompany | Knowledge work | 42.9% | source |
| WebDev Arena | Coding | 1367 | source |
API hosts
Live prices and uptime for every host serving DeepSeek V3.2 via OpenRouter.
| Host | Input | Output | Cache read | Agent $/M | Uptime 24h | Quant |
|---|---|---|---|---|---|---|
| GMICloud | $0.21 | $0.31 | $0.022 | $0.060 | 99.7% | fp8 |
| Baidu | $0.28 | $0.42 | $0.028 | $0.080 | 99.8% | fp8 |
| AtlasCloud | $0.26 | $0.38 | $0.13 | $0.16 | 56.7% | fp8 |
| DeepInfra | $0.26 | $0.38 | $0.13 | $0.16 | 99.9% | fp4 |
| DigitalOcean | $0.30 | $0.96 | $0.090 | $0.16 | 98.6% | — |
| SiliconFlow | $0.26 | $0.80 | $0.14 | $0.19 | 100.0% | fp8 |