GPT-4o (2024-11-20)
| Released | 2024-11-20 |
|---|---|
| Price per 1M | $2.50 in · $10.00 out |
| Overall score | 36.3 · rank 212 |
| Context window | 128,000 tokens |
| Provider | OpenAI |
| Weights | Proprietary |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 36.3 | 212 | 17 |
| Overall: Coding | 35.1 | 210 | 9 |
| Overall: Reasoning | 36.7 | 211 | 10 |
| Overall: Agentic work | 36.3 | 209 | 9 |
| Overall: Frontend | 37.2 | 190 | 7 |
| Coding | 34.2 | 194 | 4 |
| Reasoning | 39.8 | 196 | 5 |
| Math | 34.8 | 180 | 3 |
| Knowledge | 32.9 | 156 | 2 |
| Multimodal | 46.2 | 89 | 3 |
| Value vs price | −15.8 | 191 |
Configurations
| Configuration | Balanced | Benchmarks |
|---|---|---|
| Unspecified setting | 36.3 ±2.5 | 14 |
| High | 37.1 ±4.0 | 4 |
Evidence
Coding 34.2 ±1.9
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Aider Polyglot | 18.2% | Epoch AI | 2026-11-11 |
| GSO | 0.0% | Epoch AI | 2026-11-11 |
| SWE-bench Verified (Epoch run) | 31.0% | Epoch AI | 2026-02-11 |
| LiveCodeBench (Vals run) | 43.4% | Vals AI | 2026-09-01 |
Reasoning 39.8 ±2.0
| Benchmark | Result | Source | Date |
|---|---|---|---|
| ARC-AGI-2 | 0.0% | Epoch AI | 2026-11-11 |
| ARC-AGI-1 | 4.5% | Epoch AI | 2026-11-11 |
| CritPt | 0.0% | Epoch AI | 2026-11-11 |
| EnigmaEval | 0.8% | Epoch AI | 2026-11-11 |
| GPQA Diamond | 47.9% | Epoch AI | 2025-02-05 |
| GPQA Diamond (Vals run) | 53.8% | Vals AI | 2026-09-01 |
Math 34.8 ±2.0
| Benchmark | Result | Source | Date |
|---|---|---|---|
| FrontierMath Tiers 1-3 (2025 set) | 0.3% | Epoch AI | 2025-03-06 |
| MATH Level 5 | 49.8% | Epoch AI | 2025-02-05 |
| OTIS Mock AIME 2024-2025 | 6.3% | Epoch AI | 2025-02-25 |
Knowledge 32.9 ±1.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Humanity's Last Exam | 2.7% | Epoch AI | 2026-11-11 |
| MMLU-Pro (Vals run) | 72.6% | Vals AI | 2026-09-01 |
Multimodal 46.2 ±9.9
| Benchmark | Result | Source | Date |
|---|---|---|---|
| VPCT | 40.0% | Epoch AI | 2026-11-11 |
| MMMU-Pro (Vals run) | 62.2% | Vals AI | 2026-09-01 |
| GeoBench | 71.0% | Epoch AI | 2026-11-11 |
Names matched to this model
chatgpt-4o-11-20-2024, gpt-4o-2024-11-20