GPT-5 Pro
| Released | 2025-10-06 |
|---|---|
| Price per 1M | $15.00 in · $120.00 out |
| Overall score | 56.4 (early, few results) |
| Context window | 400,000 tokens |
| Provider | OpenAI |
| Weights | Proprietary |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 56.4 | 9 | |
| Overall: Coding | 56.1 | 6 | |
| Overall: Reasoning | 56.5 | 9 | |
| Overall: Agentic work | 56.1 | 6 | |
| Reasoning | 56.1 | 6 | |
| Math | 56.9 | 2 | |
| Knowledge | 56.5 | 1 | |
| Value vs price | −2.4 |
Configurations
| Configuration | Balanced | Benchmarks |
|---|---|---|
| Unspecified setting | 56.0 ±4.9 | 6 |
| High | 57.6 ±5.5 | 5 |
Evidence
Reasoning 56.1 ±2.1
| Benchmark | Result | Source | Date |
|---|---|---|---|
| ARC-AGI-2 | 18.3% | Epoch AI | 2026-11-11 |
| ARC-AGI-2 (ARC Prize verified) | 18.3% | ARC Prize | 2026-11-11 |
| ARC-AGI-1 (ARC Prize verified) | 70.2% | ARC Prize | 2026-11-11 |
| ARC-AGI-1 | 70.2% | Epoch AI | 2026-11-11 |
| EnigmaEval | 18.8% | Epoch AI | 2026-11-11 |
| Kagi Reasoning Benchmark | 76.8% | Kagi | 2026-11-11 |
| Chess Puzzles | 48.0% | Epoch AI | 2026-10-14 |
| SimpleBench | 61.6% | SimpleBench | 2025-10-22 |
| SimpleBench | 61.6% | Epoch AI | 2026-11-11 |
Math 56.9 ±1.2
| Benchmark | Result | Source | Date |
|---|---|---|---|
| FrontierMath Tiers 1-3 | 55.8% | Epoch AI | 2026-06-12 |
| FrontierMath Tier 4 | 19.5% | Epoch AI | 2026-06-12 |
| FrontierMath Tier 4 (2025 set) | 14.6% | Epoch AI | 2025-10-09 |
Knowledge 56.5 ±1.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Humanity's Last Exam | 31.6% | Epoch AI | 2026-11-11 |
Results not used in the score
| Benchmark | Result | Source | Why not used |
|---|---|---|---|
| ARC-AGI-1 | 70.2% | Epoch AI | A stronger configuration result was used |
| SimpleBench | 61.6% | Epoch AI | A stronger configuration result was used |
Names matched to this model
gpt-5-pro, gpt-5-pro-2025-10-06