GPT-5.5 Instant: benchmark results
OpenAI's fast GPT-5.5 Instant tier for low-latency chat. Provider: OpenAI. Released 2026-04-23. Access: API.
Aggregate Rating 1737 ± 20, rank #129 of 1656 rated models, from 104 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MapTab (Metromap, Edge Table Only) | 88.75 | Exact match accuracy (%) of the planned route on MapTab's 1, | 100 |
| MapTab (Metromap, Map + Edge Table) | 85.31 | Exact match accuracy (%) of the planned route on MapTab's 1, | 100 |
| MapTab (Metromap, Map + Edge and Vertex Tables) | 88.88 | Exact match accuracy (%) of the planned route on MapTab's 1, | 100 |
| MapTab (Metromap, Map + Mixed Table) | 69.5 | Exact match accuracy (%) of the planned route on MapTab's 1, | 100 |
| OpenAI GPT-5.6 August Update System Card - Adversarial User Simulations - Mental Health | 99.6 | not_unsafe message rate (%) | 100 |
| Chatbot Arena (Text - Spanish) | 1485 | Arena Score | 96.3 |
| MapTab (Metromap, Map-Only) | 43.63 | Exact match accuracy (%) of the planned route on MapTab's 1, | 95 |
| MapTab (Travelmap, Edge Table Only) | 98.51 | Exact match accuracy (%) of the planned route on MapTab's 1, | 95 |
| MapTab (Travelmap, Map + Edge Table) | 98.04 | Exact match accuracy (%) of the planned route on MapTab's 1, | 95 |
| MapTab (Travelmap, Map + Edge and Vertex Tables) | 83.99 | Exact match accuracy (%) of the planned route on MapTab's 1, | 95 |
| MapTab (Travelmap, Map + Mixed Table) | 57.98 | Exact match accuracy (%) of the planned route on MapTab's 1, | 95 |
| MapTab (Travelmap, Map-Only) | 68.15 | Exact match accuracy (%) of the planned route on MapTab's 1, | 95 |
Interactive version: theaggregate.ai/model?slug=gpt-5-5-instant · How It Works · Data refreshed daily, snapshot 2026-10-20.