GPT-5.5 Instant (May 2026): benchmark results
Provider: OpenAI. Released 2026-04-23. Access: API.
Unified ELO 1646 ± 1, rank #257 of 1761 rated models, from 18 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA Omniscience - Software Engineering (SWE) | 77.5 | Accuracy (%) | 94.3 |
| AA Omniscience - Health | 44.1 | Accuracy (%) | 92.2 |
| AA-Omniscience Accuracy | 46.25 | Accuracy (%) | 89.3 |
| AA Terminal-Bench Hard | 42.42 | Accuracy (%) | 89.2 |
| AA Omniscience | 11.15 | Score | 88.1 |
| AA IFBench | 71.5 | Accuracy (%) | 87.9 |
| AA Omniscience - Humanities & Social Sciences | 40.6 | Accuracy (%) | 86.7 |
| AA Omniscience - Law | 36.8 | Accuracy (%) | 86 |
| AA Omniscience - Business | 34.9 | Accuracy (%) | 85.6 |
| AA Omniscience - Science, Engineering & Mathematics | 43.6 | Accuracy (%) | 84.1 |
| AA GPQA Diamond | 84.65 | Accuracy (%) | 77.2 |
| Artificial Analysis Intelligence Index | 26.7 | Intelligence Index | 75.6 |
Interactive version: theaggregate.ai/model?slug=gpt-5-5-instant-may-2026 · How It Works · Data refreshed daily, snapshot 2026-09-05.