GPT-4.5
| Released | 2025-02-27 |
|---|---|
| Price per 1M | Not listed |
| Overall score | 43.2 · rank 173 |
| Provider | OpenAI |
| Weights | Proprietary |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 43.2 | 173 | 13 |
| Overall: Coding | 41.4 | 180 | 6 |
| Overall: Reasoning | 42.2 | 180 | 8 |
| Overall: Agentic work | 42.1 | 179 | 6 |
| Overall: Frontend | 43.5 | 153 | 3 |
| Coding | 40.9 | 175 | 1 |
| Reasoning | 44.0 | 163 | 5 |
| Math | 41.8 | 157 | 2 |
| Knowledge | 38.9 | 144 | 1 |
| General | 49.3 | 113 | 2 |
| Multimodal | 51.0 | 68 | 2 |
Evidence
Coding 40.9 ±1.5
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Aider Polyglot | 44.9% | Epoch AI | 2026-11-11 |
Reasoning 44.0 ±2.0
| Benchmark | Result | Source | Date |
|---|---|---|---|
| GPQA Diamond | 68.7% | Epoch AI | 2025-02-28 |
| ARC-AGI-2 | 0.8% | Epoch AI | 2026-11-11 |
| ARC-AGI-2 (ARC Prize verified) | 0.8% | ARC Prize | 2026-11-11 |
| ARC-AGI-1 (ARC Prize verified) | 10.3% | ARC Prize | 2026-11-11 |
| ARC-AGI-1 | 10.3% | Epoch AI | 2026-11-11 |
| EnigmaEval | 3.2% | Epoch AI | 2026-11-11 |
| SimpleBench | 34.5% | SimpleBench | 2026-11-11 |
| SimpleBench | 34.5% | Epoch AI | 2026-11-11 |
Math 41.8 ±2.0
| Benchmark | Result | Source | Date |
|---|---|---|---|
| MATH Level 5 | 78.6% | Epoch AI | 2025-02-28 |
| OTIS Mock AIME 2024-2025 | 37.8% | Epoch AI | 2025-02-28 |
Knowledge 38.9 ±1.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Humanity's Last Exam | 5.4% | Epoch AI | 2026-11-11 |
General 49.3 ±2.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| EQ-Bench Creative Writing v3 | 1,259 | EQ-Bench | 2026-11-11 |
| LMArena Text | 1,445 | LMArena | 2026-11-09 |
Multimodal 51.0 ±3.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| LMArena Vision | 1,225 | LMArena | 2026-11-09 |
| VPCT | 45.0% | Epoch AI | 2026-11-11 |
Names matched to this model
gpt-4-5, gpt-4-5-preview-2025-02-27