GPT-5.2 Pro
Higher-accuracy GPT-5.2 variant for tougher reasoning and review workflows
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
58
estimated
Long-horizon autonomy
62
estimated
Knowledge-work agents
42
estimated
Computer use
41
estimated
Security & context learning
52
estimated
Agentic benchmarks
| Benchmark | Score | Normalised | Index weight | Harness / source |
|---|---|---|---|---|
| SWE-bench Verified | est. | 8% | predicted 80 | |
| Terminal-Bench 2.0 | est. | 8% | predicted 79 | |
| DeepSWE | est. | 6% | predicted 56 | |
| FrontierSWE | est. | 5% | predicted 22 | |
| CursorBench | est. | 4% | predicted 41 | |
| GSO-Bench | est. | 4% | predicted 37 | |
| METR Time Horizons | est. | 10% | predicted 78 | |
| Vending-Bench 2 | est. | 6% | predicted 60 | |
| PostTrainBench | est. | 4% | predicted 27 | |
| APEX-Agents | est. | 8% | predicted 51 | |
| GDPval | est. | 7% | predicted 52 | |
| Remote Labor Index | est. | 5% | predicted 5 | |
| DeepResearch Bench | est. | 5% | predicted 49 | |
| OSWorld 2.0 | est. | 6% | predicted 13 | |
| OSWorld | est. | 4% | predicted 82 | |
| Cybench | est. | 5% | predicted 80 | |
| CL-bench | est. | 5% | predicted 23 |
Other benchmarks
| Benchmark | Category | Score | Source |
|---|---|---|---|
| ARC-AGI | Reasoning | 90.5% | source |
| ARC-AGI-2 | Reasoning | 54.2% | source |
| Chess Puzzles | Reasoning | 60.0% | source |
| FrontierMath Tiers 1-3 | Math | 74.0% | source |
| FrontierMath Tier 4 | Math | 46.0% | source |
| SimpleBench | Reasoning | 57.4% | source |
API hosts
Live prices and uptime for every host serving GPT-5.2 Pro via OpenRouter.
| Host | Input | Output | Cache read | Agent $/M | Uptime 24h | Quant |
|---|---|---|---|---|---|---|
| OpenAI | $21.00 | $168.00 | — | $28.00 | 100.0% | — |