GPT-5.4 Pro
| Released | 2026-03-05 |
|---|---|
| Price per 1M | $30.00 in · $180.00 out |
| Overall score | 62.4 (early, few results) |
| Context window | 1,050,000 tokens |
| Provider | OpenAI |
| Weights | Proprietary |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 62.4 | 11 | |
| Overall: Coding | 64.3 | 7 | |
| Overall: Reasoning | 62.6 | 11 | |
| Overall: Agentic work | 64.3 | 7 | |
| Reasoning | 64.3 | 7 | |
| Math | 61.8 | 2 | |
| Knowledge | 60.1 | 2 | |
| Value vs price | +2.0 |
Configurations
| Configuration | Balanced | Benchmarks |
|---|---|---|
| Unspecified setting | 61.9 ±4.6 | 4 |
| Extra High | 61.1 ±4.3 | 8 |
Evidence
Reasoning 64.3 ±1.8
| Benchmark | Result | Source | Date |
|---|---|---|---|
| ARC-AGI-2 | 83.3% | Epoch AI | 2026-11-11 |
| ARC-AGI-2 (ARC Prize verified) | 83.3% | ARC Prize | 2026-11-11 |
| GPQA Diamond | 94.6% | Epoch AI | 2026-03-20 |
| CritPt | 30.0% | Epoch AI | 2026-11-11 |
| ARC-AGI-1 (ARC Prize verified) | 94.5% | ARC Prize | 2026-11-11 |
| ARC-AGI-1 | 94.5% | Epoch AI | 2026-11-11 |
| EnigmaEval | 23.8% | Epoch AI | 2026-11-11 |
| SimpleBench | 74.1% | Epoch AI | 2026-11-11 |
| Chess Puzzles | 59.0% | Epoch AI | 2026-10-14 |
Math 61.8 ±1.5
| Benchmark | Result | Source | Date |
|---|---|---|---|
| FrontierMath Tiers 1-3 | 82.5% | Epoch AI | 2026-06-13 |
| FrontierMath Tier 4 | 58.5% | Epoch AI | 2026-06-13 |
| FrontierMath Tiers 1-3 (2025 set) | 50.0% | Epoch AI | 2026-03-06 |
| FrontierMath Tier 4 (2025 set) | 37.5% | Epoch AI | 2026-03-06 |
Knowledge 60.1 ±1.2
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Humanity's Last Exam | 44.3% | Epoch AI | 2026-11-11 |
| SimpleQA Verified | 46.3% | Epoch AI | 2026-08-27 |
Names matched to this model
gpt-5-4-pro, gpt-5-4-pro-2026-03-05, gpt-5-4-pro-2026-03-05-web-app