Indicators / series
epoch_bench.gemini_2_5_flash_preview_05_20_23k_recx5wzppdxh99q0w.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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 9d6041f53319b2b4 | 2.5% | grade B, evidence tier 6 | 2025-05-20 | 2025-05-20 | 6 | reported | api | approved | 2026-09-22 07:42 | 200 | 40d94ce2d881 | — | source page |
Raw snippets and dispute text
- 9d6041f53319b2b4 {"Cost per task": "0.3191", "Model version": "gemini-2.5-flash-preview-05-20_23K", "Name": "Gemini 2.5 Flash (Preview) (Thinking 24K)", "Organization": "Google DeepMind", "Release date": "2025-05-20", "Score": "0.025400000000000002", "id": "recX5WZPpdxH99Q0W"}