OpenAI
GPT-4o (Nov 2024)
- Announced
- Access
- Public
Benchmark scores
| Test | Score | Best on the tracker | How it was measured |
|---|---|---|---|
| Humanity's Last Examexpert questions, no tools | 2.7% | GPT-6 Astra 55% | Independentleaderboard entry "GPT-4o (November 2024)" (gpt-4o-2024-11-20) |
| GPQA DiamondPhD-level science questionsPhD experts: 70%Saturated | 48% | Gemini 4 Argon 96% | Independentdefault settings (gpt-4o-2024-11-20)Run 5 Feb 2025 |
| ARC-AGI-2visual puzzles, model aloneAverage person: 60%Saturated | 0% | GPT-6 Astra 95% | IndependentARC Prize config "GPT-4o" (gpt-4o-2024-11-20) |
| OTIS Mock AIMEcompetition mathsSaturated | 6.3% | GPT-5.5 100% | Independentdefault settings (gpt-4o-2024-11-20)Run 25 Feb 2025 |
| SWE-bench Verifiedfixing real software bugsKnown flaws | 31% | Claude Opus 4.7 83% | Independentdefault settings (gpt-4o-2024-11-20)Run 11 Feb 2026 |
Sources
- Epoch AI Benchmarking Hub (model release dates and runs)Epoch AI · Dataset · 9 Nov 2026 · epoch.ai