GPT-5.1 Instant: benchmark results
OpenAI's fast GPT-5.1 Instant tier for low-latency chat. Provider: OpenAI. Released 2025-11-12. Access: API.
Aggregate Rating 1663 ± 14, rank #284 of 1656 rated models, from 59 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MHGraphBench - Entity Clustering | 92.35 | Accuracy (%) on the 2,000 five-entity odd-one-out entity clu | 100 |
| PodBench | 82.58 | PodBench Score (0-100; mean of instruction following and scr | 100 |
| PodBench - Script Quality | 69.64 | Podcast Script Quality (0-100 rubric: depth 45, structure 30 | 100 |
| MHGraphBench - Entity Typing | 98.27 | Accuracy (%) on the 1,847 five-way entity typing items, lett | 92.9 |
| MHGraphBench - Relation Prediction | 58.08 | Accuracy (%) on the 1,634 four-way drug-disease relation pre | 92.9 |
| UGI - Writing | 60.25 | Writing Score | 91.7 |
| AI Chess Leaderboard (Continuation) | 1363 | Elo | 91.5 |
| UGI - Natural Intelligence | 58.31 | NatInt Score | 91.4 |
| BenchTable - STEM | 77.6 | Weighted Score (%) | 89.2 |
| PodBench - Instruction Following | 95.52 | Instruction Following (0-100; judge-derived checklist, items | 88.9 |
| MHGraphBench - Two-hop Selection | 60.83 | Accuracy (%) on the 1,200 two-hop selection items, letter-on | 85.7 |
| MHGraphBench - Two-hop Selection with Evidence | 64.42 | Accuracy (%) on the 1,200 two-hop selection items with sanit | 85.7 |
Interactive version: theaggregate.ai/model?slug=gpt-5-1-instant · How It Works · Data refreshed daily, snapshot 2026-10-20.