OpenAI
GPT-4.5 benchmark results
7 results on 7 benchmarks from 3 sources.
Closed Released: Feb 27, 2025 Updated Oct 22, 2026
Also listed as: gpt-4.5-preview-2025-02-27 · GPT-4.5 Preview (Feb 2025) · GPT 4.5 Preview
All benchmark results
| Benchmarks | Score | Rank | Setting | Source type | Date |
|---|---|---|---|---|---|
| LMArena Text | 1445 | 87 | Overall, style control on; 14547 votes; 95% CI 1439–1450“gpt-4.5-preview-2025-02-27” | Official leaderboard | Oct 8, 2026 |
| LMArena Vision | 1225 | 71 | Overall, style control on; 2925 votes; 95% CI 1213–1237“gpt-4.5-preview-2025-02-27” | Official leaderboard | Oct 2, 2026 |
| GPQA Diamond | 68.7% | 164 | Epoch AI run, accuracy; effort: Feb 2025 | Independent run | Feb 28, 2025 |
| MMLU-Pro | 86.1% | 27 | Overall accuracy; data source: Self-Reported | Vendor-reported | Mar 11, 2026 |
| AIME (OTIS Mock AIME 2024–2025) | 37.8% | 183 | Epoch AI run, OTIS Mock AIME 2024–2025; effort: Feb 2025 | Independent run | Feb 28, 2025 |
| MATH Level 5 | 78.6% | 37 | Epoch AI run, accuracy; effort: Feb 2025 | Independent run | Feb 28, 2025 |
| Humanity's Last Exam | 5.4% | 44 | Compiled by Epoch AI; effort: Feb 2025 | Third-party compilation via Epoch AI | Feb 27, 2025 |
FAQ
Where do these GPT-4.5 scores come from?
From Epoch AI Benchmarking Hub, LMArena leaderboard dataset, and MMLU-Pro leaderboard (TIGER-Lab). Each row links to the original leaderboard, dataset or report, and vendor-reported numbers are labelled.