OpenAI
GPT-4o mini benchmark results
9 results on 8 benchmarks from 4 sources.
Also listed as: gpt-4o-mini-2024-07-18 · GPT 4o-mini · GPT-4o mini (2024-07-18) · GPT-4O-mini-2024-07-18 · GPT-4o-mini
All benchmark results
| Benchmarks | Score | Rank | Setting | Source type | Date |
|---|---|---|---|---|---|
| LMArena Text | 1318 | 263 | Overall, style control on; 68705 votes; 95% CI 1314–1321“gpt-4o-mini-2024-07-18” | Official leaderboard | Oct 8, 2026 |
| LMArena Vision | 1097 | 129 | Overall, style control on; 17341 votes; 95% CI 1089–1105“gpt-4o-mini-2024-07-18” | Official leaderboard | Oct 2, 2026 |
| LiveCodeBench | 26.7% | 20 | Code generation, 182 problems dated 2025-01-01…2025-04-07“GPT-4O-mini-2024-07-18” | Official leaderboard | Apr 7, 2025 |
| GPQA Diamond | 37.7% | 243 | Epoch AI run, accuracy | Independent run | Jan 27, 2025 |
| MMLU | 81.8% | 11 | Exact match; 5-shot | Paper / tech report via Epoch AI | Jul 18, 2024 |
| MMLU | 76.7% | 35 | Exact match; 5-shot | Official leaderboard via Epoch AI | Jul 18, 2024 |
| MMLU-Pro | 63.1% | 128 | Overall accuracy; data source: TIGER-Lab“GPT-4o-mini” | Official leaderboard | Mar 11, 2026 |
| AIME (OTIS Mock AIME 2024–2025) | 6.9% | 224 | Epoch AI run, OTIS Mock AIME 2024–2025 | Independent run | Jul 30, 2025 |
| MATH Level 5 | 52.6% | 57 | Epoch AI run, accuracy | Independent run | Jan 27, 2025 |
FAQ
Where do these GPT-4o mini scores come from?
From Epoch AI Benchmarking Hub, LiveCodeBench leaderboard, 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.