GPT-5.5 Instant (May 2026): benchmark results
Provider: OpenAI. Released 2026-04-23. Access: API.
Aggregate Rating 1704 ± 39, rank #328 of 10916 rated models, from 8 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA Terminal-Bench Hard | 42.42 | Accuracy (%) | 89.2 |
| AA IFBench | 71.5 | Accuracy (%) | 87.9 |
| AA GPQA Diamond | 84.65 | Accuracy (%) | 77.3 |
| AA Humanity's Last Exam | 21.59 | Accuracy (%) | 67.3 |
| AA CritPt | 2.57 | Accuracy (%) | 63.4 |
| AA Long Context Reasoning | 66.33 | Accuracy (%) | 55.4 |
| Tau2-Bench Telecom | 49.42 | Success Rate (%) | 53.9 |
| AA TAU-2 Bench | 49.42 | Accuracy (%) | 52.4 |
Interactive version: theaggregate.ai/model?slug=gpt-5-5-instant-may-2026 · How It Works · Data refreshed daily, snapshot 2026-11-08.