GPT-5.5 Pro
| Released | 2026-04-23 |
|---|---|
| Price per 1M | $30.00 in · $180.00 out |
| Overall score | 64.8 (early, few results) |
| Context window | 1,050,000 tokens |
| Provider | OpenAI |
| Weights | Proprietary |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 64.8 | 9 | |
| Overall: Coding | 65.1 | 6 | |
| Overall: Reasoning | 64.8 | 9 | |
| Overall: Agentic work | 65.1 | 6 | |
| Reasoning | 65.1 | 6 | |
| Math | 64.3 | 3 | |
| Value vs price | +4.6 |
Configurations
| Configuration | Balanced | Benchmarks |
|---|---|---|
| Unspecified setting | 64.5 ±8.3 | 1 |
| High | 63.4 ±5.2 | 5 |
| Extra High | 64.6 ±4.9 | 8 |
Evidence
Reasoning 65.1 ±1.9
| Benchmark | Result | Source | Date |
|---|---|---|---|
| ARC-AGI-2 | 84.6% | Epoch AI | 2026-11-11 |
| ARC-AGI-2 (ARC Prize verified) | 84.6% | ARC Prize | 2026-11-11 |
| GPQA Diamond | 93.9% | Epoch AI | 2026-04-24 |
| CritPt | 30.6% | Epoch AI | 2026-11-11 |
| ARC-AGI-1 (ARC Prize verified) | 96.5% | ARC Prize | 2026-11-11 |
| ARC-AGI-1 | 96.5% | Epoch AI | 2026-11-11 |
| Chess Puzzles | 62.0% | Epoch AI | 2026-10-14 |
| SimpleBench | 76.9% | SimpleBench | 2026-04-24 |
| SimpleBench | 76.9% | Epoch AI | 2026-11-11 |
Math 64.3 ±2.0
| Benchmark | Result | Source | Date |
|---|---|---|---|
| OTIS Mock AIME 2024-2025 | 100.0% | Epoch AI | 2026-04-24 |
| FrontierMath Tier 4 | 78.1% | Epoch AI | 2026-06-12 |
| FrontierMath Tiers 1-3 | 87.7% | Epoch AI | 2026-06-12 |
| FrontierMath Tiers 1-3 (2025 set) | 52.4% | Epoch AI | 2026-04-23 |
| FrontierMath Tier 4 (2025 set) | 39.6% | Epoch AI | 2026-04-23 |
Results not used in the score
| Benchmark | Result | Source | Why not used |
|---|---|---|---|
| ARC-AGI-1 | 95.0% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-1 (ARC Prize verified) | 95.0% | ARC Prize | A stronger configuration result was used |
| ARC-AGI-2 | 84.2% | Epoch AI | A stronger configuration result was used |
| ARC-AGI-2 (ARC Prize verified) | 84.2% | ARC Prize | A stronger configuration result was used |
| FrontierMath Tier 4 (2025 set) | 39.6% | Epoch AI | A stronger configuration result was used |
| FrontierMath Tiers 1-3 (2025 set) | 51.0% | Epoch AI | A stronger configuration result was used |
| SimpleBench | 76.9% | Epoch AI | A stronger configuration result was used |
Names matched to this model
gpt-5-5-pro, gpt-5-5-pro-pre-release