GPT-4
| Released | 2023-11-06 |
|---|---|
| Price per 1M | $30.00 in · $60.00 out |
| Overall score | 31.5 · rank 228 |
| Context window | 8,192 tokens |
| Provider | OpenAI |
| Weights | Proprietary |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 31.5 | 228 | 7 |
| Overall: Coding | 31.8 | 225 | 3 |
| Overall: Reasoning | 32.0 | 227 | 4 |
| Overall: Agentic work | 31.4 | 228 | 3 |
| Agents | 30.6 | 181 | 1 |
| Reasoning | 34.3 | 222 | 2 |
| Math | 29.1 | 193 | 2 |
| General | 31.3 | 182 | 2 |
| Value vs price | −27.1 | 195 |
Evidence
Agents 30.6 ±2.6
| Benchmark | Result | Source | Date |
|---|---|---|---|
| METR 50% Time Horizon | $4 | METR | 2026-11-11 |
| METR task suite | 36.1% | Epoch AI | 2026-11-11 |
Reasoning 34.3 ±4.2
| Benchmark | Result | Source | Date |
|---|---|---|---|
| GPQA Diamond | 35.7% | Epoch AI | 2025-10-23 |
| Mystery Game Puzzles | 12.0% | Epoch AI | 2026-08-28 |
Math 29.1 ±2.0
| Benchmark | Result | Source | Date |
|---|---|---|---|
| MATH Level 5 | 23.0% | Epoch AI | 2025-01-27 |
| OTIS Mock AIME 2024-2025 | 1.1% | Epoch AI | 2025-10-23 |
General 31.3 ±2.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| EQ-Bench Creative Writing v3 | 750 | EQ-Bench | 2026-11-11 |
| LMArena Text | 1,288 | LMArena | 2026-11-09 |
Names matched to this model
gpt-4, gpt-4-0314, gpt-4-0613, gpt-4-32k-0314, gpt-4-32k-0613