GPT-4o (2024-11-20)
GPT / OpenAI
23scores
23benchmarks
$2.5 / $10 per 1M tokenscost in/out
Metadata
GPT Closed/API
Aliases: gpt-4o-2024-11-20, openai-gpt-4o-2024-11-20, openai/gpt-4o-2024-11-20
| Benchmark | Category | Rank | Score | Sampled |
|---|---|---|---|---|
| ARC-AGI-1 | Agentic | 137 | 4.50 | 2026-05-05 |
| ARC-AGI-2 | Agentic | 131 | 0 | 2026-05-05 |
| AgentBench FC | Agents | 20 | 39.60 | 2026-05-06 |
| BigCodeBench | Coding | 13 | 48 | 2026-05-06 |
| BigCodeBench-Hard | Coding | 25 | 27.70 | 2026-05-05 |
| LiveCodeBench | Coding | 94 | 43.444% | 2026-05-28 |
| MMTU | Data | 13 | 0.51 | 2026-05-06 |
| CorpFin v2 | Finance | 91 | 45.921% | 2026-05-28 |
| MortgageTax | Finance | 53 | 57.432% | 2026-05-28 |
| TaxEval v2 | Finance | 19 | 74.53% | 2026-05-28 |
| GPQA Diamond | Intelligence | 90 | 53.788% | 2026-05-28 |
| MMLU Pro | Intelligence | 88 | 72.563% | 2026-05-28 |
| MMMU Pro | Intelligence | 63 | 62.161% | 2026-05-28 |
| HindiGen v1 | Language | 10 | 72.44 | 2026-05-06 |
| CaseLaw v2 | Legal | 26 | 59.7% | 2026-05-04 |
| J1-ENVS | Legal | 1 | 63.90 | 2026-05-26 |
| LegalBench | Legal | 42 | 82.214% | 2026-05-28 |
| AIME | Math | 87 | 11.875% | 2026-04-16 |
| MATH 500 | Math | 47 | 74% | 2026-01-09 |
| MGSM | Math | 41 | 90.364% | 2026-01-09 |
| CAIS Text Capabilities Index | Reasoning | 37 | 5.2 | 2026-05-27 |
| CAIS Risk Index | Safety | 37 | 67.0 | 2026-05-27 |
| CAIS Vision Capabilities Index | Vision | 27 | 43.4 | 2026-05-27 |
No matching rows.