Indicators / series
epoch_bench.gpt_5_4_mini_2026_03_17_xhigh_jtq6rdinxjnkkvmepbe3ub.frontiermath_t4.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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 279e49625b5cf876 | 9.8% | grade A, evidence tier 1 | 2026-03-17 | 2026-06-12 | 1 | reported | api | approved | 2026-09-22 10:28 | 200 | 55692b9c1ecf | — | source page |
Raw snippets and dispute text
- 279e49625b5cf876 {"Best score (across scorers)": "0.0975609756097561", "Cost per task": null, "Model version": "gpt-5.4-mini-2026-03-17_xhigh", "Name": null, "Organization": "OpenAI", "Release date": "2026-03-17", "Started at": "2026-06-12T16:40:39.000Z", "id": "jtQ6rDiNxjNKkVMEPBE3Ub"}