GPT-5.1 (Low) — benchmark results
GPT-5.1 evaluated at the low reasoning-effort setting. Provider: OpenAI. Released 2025-11-12. Access: API.
Unified ELO 1711 ± 23, rank #255 of 1776 rated models, from 21 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| UGI - Natural Intelligence | 61.99 | NatInt Score | 95.4 |
| UGI - Writing | 50.84 | Writing Score | 89.2 |
| LLM Chess (Saplin) | 614.7 | ELO | 85 |
| UGI Leaderboard | 44.15 | UGI Score | 77.9 |
| Epoch AI - ECI | 149.74 | ECI Score | 73.9 |
| Design Arena (Data Viz) | 1241 | Elo | 73.6 |
| Design Arena (Game Dev) | 1209 | Elo | 57.9 |
| FrontierMath - Tiers 1-3 | 17.3 | Accuracy (%, 290 problems) | 54.5 |
| Design Arena (Website) | 1199 | Elo | 53.8 |
| Design Arena (UI Components) | 1195 | Elo | 50.7 |
| OTIS Mock AIME 2024-25 | 63.89 | Accuracy (%) | 50.3 |
| Design Arena (SVG) | 1165 | Elo | 45.5 |
Interactive version: theaggregate.ai/model?slug=gpt-5-1-low · How the rankings work · Data refreshed daily, snapshot 2026-07-22.