GPT-5.4 Low
| Released | 2026-03-05 |
|---|---|
| Price per 1M | $2.50 in · $15.00 out |
| Overall score | 47.9 (early, few results) |
| Context window | 1,050,000 tokens |
| Provider | OpenAI |
| Weights | Proprietary |
| Configuration | Low |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 47.9 | 7 | |
| Overall: Coding | 45.4 | 6 | |
| Overall: Reasoning | 53.7 | 6 | |
| Overall: Agentic work | 43.4 | 6 | |
| Agents | 40.5 | 1 | |
| Reasoning | 55.0 | 5 | |
| Math | 52.0 | 1 | |
| Value vs price | −7.2 |
Evidence
Agents 40.5 ±6.1
| Benchmark | Result | Source | Date |
|---|---|---|---|
| DeepResearch Bench | 35.1% | Epoch AI | 2026-11-11 |
Reasoning 55.0 ±2.2
| Benchmark | Result | Source | Date |
|---|---|---|---|
| GPQA Diamond | 84.9% | Epoch AI | 2026-07-15 |
| ARC-AGI-2 | 29.2% | Epoch AI | 2026-11-11 |
| ARC-AGI-2 (ARC Prize verified) | 29.2% | ARC Prize | 2026-11-11 |
| ARC-AGI-1 (ARC Prize verified) | 68.2% | ARC Prize | 2026-11-11 |
| ARC-AGI-1 | 68.2% | Epoch AI | 2026-11-11 |
| Chess Puzzles | 19.0% | Epoch AI | 2026-10-13 |
| Mystery Game Puzzles | 17.0% | Epoch AI | 2026-08-27 |
Math 52.0 ±3.6
| Benchmark | Result | Source | Date |
|---|---|---|---|
| OTIS Mock AIME 2024-2025 | 84.4% | Epoch AI | 2026-07-15 |
Names matched to this model
gpt-5-4-low