GPT-3.5 Turbo (0125) — benchmark results
January 25, 2024 GPT-3.5 Turbo API snapshot (gpt-3.5-turbo-0125). Provider: OpenAI. Released 2024-01-25. Access: API.
Unified ELO 1455 ± 19, rank #973 of 1776 rated models, from 84 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| SpeechMap Compliance | 94.5 | % Requests Completed | 96.7 |
| LogicKor - Grammar | 8 | Score (0-10) | 91.4 |
| LogicKor - Coding | 9.42 | Score (0-10) | 90.7 |
| LogicKor - Understanding | 9.57 | Score (0-10) | 88.9 |
| LogicKor - Single-Turn | 8.19 | Score (0-10) | 84.3 |
| LogicKor - Math | 6.92 | Score (0-10) | 83.4 |
| LogicKor - Multi-Turn | 7.88 | Score (0-10) | 83.4 |
| LogicKor | 7.78 | Score (0-10) | 82.3 |
| Compl-AI Board | 76.99 | Average Compliance Score (%) | 78.6 |
| BiGGen-Bench | 3.69 | Average Score (1-5) | 77.5 |
| LogicKor - Reasoning | 7.07 | Score (0-10) | 75.4 |
| HELM EWoK - Physical Dynamics | 87.33 | EM | 71.4 |
Interactive version: theaggregate.ai/model?slug=gpt-3-5-turbo-0125 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.