GPT-5.4 Non-reasoning
| Released | 2026-03-05 |
|---|---|
| Price per 1M | $2.50 in · $15.00 out |
| Overall score | 49.0 (early, few results) |
| Context window | 1,050,000 tokens |
| Provider | OpenAI |
| Weights | Proprietary |
| Configuration | Non-reasoning |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 49.0 | 6 | |
| Overall: Coding | 46.0 | 4 | |
| Overall: Reasoning | 46.2 | 5 | |
| Overall: Agentic work | 46.0 | 4 | |
| Reasoning | 46.0 | 4 | |
| Math | 46.4 | 1 | |
| General | 56.1 | 1 | |
| Value vs price | −6.1 |
Evidence
Reasoning 46.0 ±4.2
| Benchmark | Result | Source | Date |
|---|---|---|---|
| GPQA Diamond | 74.8% | Epoch AI | 2026-07-15 |
| Extended NYT Connections | 17.8% | Lech Mazur | 2026-11-10 |
| Chess Puzzles | 3.0% | Epoch AI | 2026-10-13 |
| Mystery Game Puzzles | 16.0% | Epoch AI | 2026-08-30 |
Math 46.4 ±3.6
| Benchmark | Result | Source | Date |
|---|---|---|---|
| OTIS Mock AIME 2024-2025 | 57.8% | Epoch AI | 2026-07-15 |
General 56.1 ±3.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LLM Debate Benchmark | 1,487 | Lech Mazur | 2026-10-26 |
Names matched to this model
gpt-5-4-non-reasoning