Indicators / series
epoch_bench.gpt_5_2_pro_2025_12_11_medium.arc_agi_2.pt
Source: Epoch AI benchmarks and Capabilities Index (Epoch AI) · CC BY 4.0 · CSV
Epoch AI, Benchmarking Hub and Epoch Capabilities Index (CC BY 4.0)
| id | value | grade | as of date | published date | tier | audited vs reported | extraction method | review status | retrieved at | http status | content hash | supersedes id | url | flags |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 437deb36e9fde815 | 38.5% | grade B, evidence tier 6 | 2025-12-11 | 2025-12-11 | 6 | reported | api | approved | 2026-09-10T06:33:11.514623Z | 200 | cde2f74ecf00 | — | source page |
Raw snippets and dispute text
- 437deb36e9fde815 {"Cost per task": "8.9928", "Model version": "gpt-5.2-pro-2025-12-11_medium", "Name": "GPT-5.2 Pro (Medium)", "Organization": "OpenAI", "Release date": "2025-12-11", "Score": "0.3847"}