Model profile
GPT-5.5 Instant
OpenAIdeveloper
2026-05-26release date
#5 / 312overall rank
4eval lineages
Evidence summary
GPT-5.5 Instant has an estimated overall rank of #5; its 90% source-sensitivity interval is #2–#82. Its behavior-only rank is #8; company governance moves the combined estimate to #5. Published evidence spans 4 evals and 3 of 7 behavior components. Its strongest relative result is Arena Factuality — Text Arena (factuality-only weighting) (factuality_bt_rating, #9 of 112); its weakest is SM-Bench (eq_boundaries, #47 of 79).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗gpt-5-5-instant-05-26
- Official model documentation ↗Family-level model document · openai · first party
- Release source ↗declared identity
Published eval results
Rank is within that sub-eval. Black marks the observed result; the grey dot marks the value implied by the global rank. Values stay on each source’s native scale.
| Eval / sub-eval | Rank | Value | Distribution | Source |
|---|---|---|---|---|
| AA-Omnisciencehallucination_rate | #93 / 330 | ↓0.653 | Source ↗official | |
| Arena Factuality — Text Arena (factuality-only weighting)factuality_bt_rating | #9 / 112 | ↑1473.0 | Source ↗official | |
| BullshitBench v2clear_pushback_rate | #43 / 106 | ↑0.34 | Source ↗official | |
| SM-Benchadversarial | #8 / 79 | ↑88.78 | Source ↗official | |
| SM-Benchambiguous_interpretation | #27 / 79 | ↑88.1 | Source ↗official | |
| SM-Benchanti_hallucination | #29 / 79 | ↑95.81 | Source ↗official | |
| SM-Bencheq_boundaries | #47 / 79 | ↑62.36 | Source ↗official | |
| SM-Benchoverfit | #31 / 79 | ↑78.96 | Source ↗official |