Rankings / OpenAI
GPT 5.5 Pre Release
released 2026-04-23
BenchAtlas Index
as of 2026-07-14
xhigh effort
rank #26
4 families · 3 categories · medium
Benchmark evidence
6 results
external indices
| ECI | xhigh effort | 158.3 points | independent | Epoch AI Benchmarking Hub |
factuality
| SimpleQA Verified | xhigh effort | 63.1 % | independent | Epoch AI Benchmarking Hub 2026-04-24 |
knowledge science
| GPQA Diamond | xhigh effort | 94.0 % | independent | Epoch AI Benchmarking Hub 2026-04-24 |
reasoning math
| FrontierMath | xhigh effort | 51.7 % | independent | Epoch AI Benchmarking Hub 2026-04-23 |
| FrontierMath Tier 4older version | xhigh effort | 35.4 % | independent | Epoch AI Benchmarking Hub 2026-04-23 |
| OTIS Mock AIME 2024–2025 | xhigh effort | 100.0 % | independent | Epoch AI Benchmarking Hub 2026-04-24 |
Agent + model results
systems, not bare-model scores
| agent + model Epoch Inspect harness + GPT 5.5 Pre Release | SWE-bench Verified | 80.6 % | independent | Epoch AI Benchmarking Hub |
These scores measure the whole agent system (scaffold, tools, budgets) — they are never merged into the bare model’s numbers.