OpenAI
GPT-4o (May 2024) benchmark results
18 results on 9 benchmarks from 5 sources.
Closed Released: May 13, 2024 Updated Oct 22, 2026
Also listed as: gpt-4o-2024-05-13 · gpt-4o-2024-08-06 · GPT-4o (2024-05-13) · GPT-4o · Agentless-1.5 + GPT 4o (2024-05-13) · AutoCodeRover (v20240620) + GPT 4o (2024-05-13) · MASAI + GPT 4o (2024-06-12) · EPAM AI/Run Developer Agent + GPT4o · AppMap Navie + GPT 4o (2024-05-13) · SWE-agent + GPT 4o (2024-05-13)
All benchmark results
| Benchmarks | Score | Rank | Setting | Source type | Date |
|---|---|---|---|---|---|
| LMArena Text | 1346 | 223 | Overall, style control on; 112881 votes; 95% CI 1343–1350“gpt-4o-2024-05-13” | Official leaderboard | Oct 8, 2026 |
| LMArena Text | 1336 | 239 | Overall, style control on; 45499 votes; 95% CI 1331–1340“gpt-4o-2024-08-06” | Official leaderboard | Oct 8, 2026 |
| LMArena Vision | 1162 | 102 | Overall, style control on; 23273 votes; 95% CI 1153–1171“gpt-4o-2024-05-13” | Official leaderboard | Oct 2, 2026 |
| LMArena Vision | 1118 | 126 | Overall, style control on; 3376 votes; 95% CI 1106–1131“gpt-4o-2024-08-06” | Official leaderboard | Oct 2, 2026 |
| LiveCodeBench | 28.4% | 18 | Code generation, 182 problems dated 2025-01-01…2025-04-07“GPT-4O-2024-08-06” | Official leaderboard | Apr 7, 2025 |
| GPQA Diamond | 48.9% | 210 | Epoch AI run, accuracy; effort: May 2024 | Independent run | Jan 27, 2025 |
| MMLU | 84.2% | 8 | Exact match; 5-shot; effort: May 2024 | Official leaderboard via Epoch AI | May 13, 2024 |
| MMLU-Pro | 77.9% | 77 | Overall accuracy; data source: Self-Reported“GPT-4o (2024-11-20)” | Vendor-reported | Mar 11, 2026 |
| MMLU-Pro | 72.5% | 93 | Overall accuracy; data source: TIGER-Lab“GPT-4o (2024-05-13)” | Official leaderboard | Mar 11, 2026 |
| SWE-bench Verified | 38.8% | 85 | agent: Agentless-1.5“gpt-4o-2024-05-13” | Official leaderboard | Oct 28, 2024 |
| SWE-bench Verified | 38.4% | 86 | agent: AutoCodeRover“gpt-4o-2024-05-13” | Official leaderboard | Jun 28, 2024 |
| SWE-bench Verified | 32.6% | 91 | agent: MASAI“gpt-4o-2024-08-06” | Official leaderboard | Jun 12, 2024 |
| SWE-bench Verified | 27.0% | 93 | agent: EPAM AI/Run Developer Agent“gpt-4o-2024-08-06” | Official leaderboard | Oct 16, 2024 |
| SWE-bench Verified | 26.2% | 94 | agent: AppMap Navie“gpt-4o-2024-05-13” | Official leaderboard | Jun 15, 2024 |
| SWE-bench Verified | 23.2% | 97 | agent: SWE-agent“gpt-4o-2024-05-13” | Official leaderboard | Jul 28, 2024 |
| SWE-bench Verified | 21.6% | 100 | agent: mini-SWE-agent“gpt-4o-20241120” | Official leaderboard | Jul 20, 2025 |
| AIME (OTIS Mock AIME 2024–2025) | 6.3% | 230 | Epoch AI run, OTIS Mock AIME 2024–2025; effort: May 2024 | Independent run | Feb 25, 2025 |
| MATH Level 5 | 51.0% | 59 | Epoch AI run, accuracy; effort: May 2024 | Independent run | Jan 27, 2025 |
FAQ
Where do these GPT-4o (May 2024) scores come from?
From Epoch AI Benchmarking Hub, LiveCodeBench leaderboard, LMArena leaderboard dataset, MMLU-Pro leaderboard (TIGER-Lab), and SWE-bench leaderboards (swebench.com). Each row links to the original leaderboard, dataset or report, and vendor-reported numbers are labelled.