GPT-5 Mini (Low): benchmark results
GPT-5 Mini evaluated at the low reasoning-effort setting. Provider: OpenAI. Released 2025-08-07. Access: API.
Aggregate Rating 1638 ± 15, rank #571 of 2168 rated models, from 65 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| GPSBench (Applied) - Proximity | 89.6 | Score (%) on the proximity (which of four named cities lies | 100 |
| PSF-Med - Frontier Hardest 500 - PadChest | 2.41 | Paraphrase Flip Rate (%) | 100 |
| PSF-Med - Frontier Hardest 500 - VinDr-CXR | 5.12 | Paraphrase Flip Rate (%) | 100 |
| GPSBench (Applied) - Route Analysis | 90.1 | Score (%) on the route analysis (whether a named waypoint ci | 92.3 |
| GPSBench (Applied) - Spatial Patterns | 95.2 | Score (%) on the spatial patterns (pick the geographic outli | 92.3 |
| GPSBench (Pure GPS) - Bearing Computation | 99.8 | Score (%) on the bearing computation (initial bearing betwee | 92.3 |
| GPSBench (Pure GPS) - Coordinate Interpolation | 54.1 | Score (%) on the coordinate interpolation (a point a quarter | 92.3 |
| GPSBench (Pure GPS) - Distance Calculation | 99.9 | Score (%) on the distance calculation (great-circle distance | 92.3 |
| GPSBench (Pure GPS) - Route Geometry | 91.8 | Score (%) on the route geometry (Ramer-Douglas-Peucker simpl | 92.3 |
| PointQ-Bench - Quality Reasoning | 8.21 | SSFRQ-5D score (0-10): sum of five 0-2 judge ratings (struct | 92.3 |
| SLR-Bench - Basic | 100 | Accuracy (%) | 86.4 |
| GPSBench (Pure GPS) - Coordinate Transformation | 79.4 | Score (%) on the coordinate transformation (WGS84 to and fro | 84.6 |
Interactive version: theaggregate.ai/model?slug=gpt-5-mini-low · How It Works · Data refreshed daily, snapshot 2026-10-20.