Model profile
GPT-5.5 Pro
2026-04-23release date
1eval lineages
1discovery sources
Evidence summary
Published evidence spans 1 evals and 1 of 7 behavior components. Its strongest relative result is BullshitBench v2 (clear_pushback_rate, #41 of 105); its weakest is BullshitBench v2 (clear_pushback_rate, #41 of 105).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗gpt-5-5-pro
- OpenRouter ↗openai/gpt-5.5-pro
- Official model documentation ↗Family-level model document · openai · first party
- Release source ↗declared identity
- openai.com ↗
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 | Better | Source |
|---|---|---|---|---|---|
| BullshitBench v2clear_pushback_rate | #41 / 105 | 0.35 | ↑ higher | Source ↗official |