GPT-5.4 Medium
| Released | 2026-03-05 |
|---|---|
| Price per 1M | $2.50 in · $15.00 out |
| Overall score | 58.4 (early, few results) |
| Context window | 1,050,000 tokens |
| Provider | OpenAI |
| Weights | Proprietary |
| Configuration | Medium |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 58.4 | 9 | |
| Overall: Coding | 51.7 | 7 | |
| Overall: Reasoning | 58.7 | 7 | |
| Overall: Agentic work | 59.7 | 6 | |
| Overall: Frontend | 46.4 | 1 | |
| Reasoning | 59.7 | 6 | |
| Math | 57.5 | 1 | |
| Frontend | 46.4 | 1 | |
| General | 63.3 | 1 | |
| Value vs price | +3.2 |
Evidence
Reasoning 59.7 ±1.8
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Extended NYT Connections | 87.8% | Lech Mazur | 2026-11-10 |
| ARC-AGI-2 | 55.4% | Epoch AI | 2026-11-11 |
| ARC-AGI-2 (ARC Prize verified) | 55.4% | ARC Prize | 2026-11-11 |
| GPQA Diamond | 88.9% | Epoch AI | 2026-07-15 |
| ARC-AGI-1 (ARC Prize verified) | 86.2% | ARC Prize | 2026-11-11 |
| ARC-AGI-1 | 86.2% | Epoch AI | 2026-11-11 |
| Chess Puzzles | 37.0% | Epoch AI | 2026-10-13 |
| Mystery Game Puzzles | 28.0% | Epoch AI | 2026-08-28 |
Math 57.5 ±3.6
| Benchmark | Result | Source | Date |
|---|---|---|---|
| OTIS Mock AIME 2024-2025 | 95.6% | Epoch AI | 2026-07-15 |
Frontend 46.4 ±3.0
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LMArena WebDev | 1,442 | LMArena | 2026-11-09 |
General 63.3 ±5.1
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Creative Story-Writing (Lech Mazur) | 77.0% | Lech Mazur | 2026-10-23 |
Names matched to this model
gpt-5-4-medium