OpenAI
GPT-3.5 Turbo (Jan 2024) benchmark results
5 results on 5 benchmarks from 2 sources.
Also listed as: gpt-3.5-turbo-0125 · GPT-3.5 Turbo (0125)
All benchmark results
| Benchmarks | Score | Rank | Setting | Source type | Date |
|---|---|---|---|---|---|
| LMArena Text | 1226 | 333 | Overall, style control on; 66207 votes; 95% CI 1221–1230“gpt-3.5-turbo-0125” | Official leaderboard | Oct 8, 2026 |
| GPQA Diamond | 27.2% | 268 | Epoch AI run, accuracy; effort: Jan 2024 | Independent run | Jan 27, 2025 |
| MMLU | 67.3% | 64 | Exact match; 5-shot; effort: Jan 2024 | Official leaderboard via Epoch AI | Jan 25, 2024 |
| AIME (OTIS Mock AIME 2024–2025) | 2.2% | 248 | Epoch AI run, OTIS Mock AIME 2024–2025; effort: Jan 2024 | Independent run | Aug 7, 2026 |
| MATH Level 5 | 11.6% | 96 | Epoch AI run, accuracy; effort: Jan 2024 | Independent run | Jan 27, 2025 |
FAQ
Where do these GPT-3.5 Turbo (Jan 2024) scores come from?
From Epoch AI Benchmarking Hub and LMArena leaderboard dataset. Each row links to the original leaderboard, dataset or report, and vendor-reported numbers are labelled.