GPT-5 Nano (Low): benchmark results
GPT-5 Nano evaluated at the low reasoning-effort setting. Provider: OpenAI. Released 2025-08-07. Access: API.
Aggregate Rating 1517 ± 23, rank #1003 of 2168 rated models, from 32 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| GPSBench (Applied) - Boundary Analysis | 98.5 | Score (%) on the boundary analysis (group four to six named | 92.3 |
| SLR-Bench - Basic | 100 | Accuracy (%) | 86.4 |
| GPSBench (Pure GPS) - Relative Position | 65.5 | Score (%) on the relative position (compass direction betwee | 76.9 |
| GPSBench (Pure GPS) - Area and Perimeter | 17.1 | Score (%) on the area and perimeter (spherical polygon of th | 69.2 |
| GPSBench (Pure GPS) - Coordinate Transformation | 54.7 | Score (%) on the coordinate transformation (WGS84 to and fro | 61.5 |
| FormationEval | 93.3 | Accuracy (%) | 57 |
| FormationEval, an open multiple-choice benchmark for petroleum geoscience | 0.93 | accuracy (rate) | 57 |
| GPSBench (Applied) - Relative Position | 52.6 | Score (%) on the relative position (compass direction betwee | 53.8 |
| ObviousBench | 90.97 | Answer pass³ (%) | 50.4 |
| GPSBench (Applied) - Terrain Classification | 67.4 | Score (%) on the terrain classification (urban, coastal, mou | 38.5 |
| LLM Chess (Saplin) | -116.98 | Native anchored-opponent Elo (signed points) | 31.6 |
| GPSBench (Applied) - Route Analysis | 84.8 | Score (%) on the route analysis (whether a named waypoint ci | 30.8 |
Interactive version: theaggregate.ai/model?slug=gpt-5-nano-low · How It Works · Data refreshed daily, snapshot 2026-10-20.