Model comparison
GPT-4.5 vs o3-pro
o3-pro is the stronger model overall, scoring 42.7 to 36.9 on the Noometry Index.
Last verified . 8 shared benchmarks.
Summary
- They share 8 benchmarks with published results for both. GPT-4.5 scores higher in 1 category and o3-pro in 4 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in long context, where o3-pro leads 72.1 to 40.4.
- The biggest single-benchmark swing is ARC-AGI-1: 10.3% for GPT-4.5 and 59.3% for o3-pro.
Side by side
| GPT-4.5 | o3-pro | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 36.9 | 42.7 |
| Released | 2025-02-27 | 2025-06-10 |
| Weights | Proprietary | Proprietary |
| Context window | — | 200K |
| Max output | — | 100K |
| Input $ / M tokens | — | $20 |
| Output $ / M tokens | — | $80 |
| Results tracked | 42 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3-pro leads
GPT-4.5: 41.8 (#102), o3-pro: 55.1 (#22)
| Benchmark | GPT-4.5 | o3-pro |
|---|---|---|
| Aider Polyglot | 44.9% | 84.9% |
| WeirdML | 39.4% | 58.2% |
| LiveBench Coding | 75.2% | — |
| LMArena Coding | 1397 | — |
Agentic & Tool Use Not comparable
GPT-4.5: 27.6 (#92), o3-pro: —
| Benchmark | GPT-4.5 | o3-pro |
|---|---|---|
| Cybench | 17.5% | — |
Reasoning o3-pro leads
GPT-4.5: 14.1 (#320), o3-pro: 24.1 (#152)
| Benchmark | GPT-4.5 | o3-pro |
|---|---|---|
| ARC-AGI-2 | 0.8% | 4.9% |
| ARC-AGI-1 | 10.3% | 59.3% |
| Epoch Capabilities Index | 136.74 | 147.43 |
| SimpleBench | 34.5% | — |
| Kagi LLM Benchmark | — | 72.1% |
| EnigmaEval | 3.2% | — |
| LiveBench Reasoning | 71.1% | — |
| LMArena Hard Prompts | 1404 | — |
| DTBench | — | 86.9% |
| LiveBench Data Analysis | 64.3% | — |
| LMCA | — | 38.5% |
| ForecastBench | 61.7 | — |
| LiveBench | 69% | — |
Math Not comparable
GPT-4.5: 31.0 (#200), o3-pro: —
| Benchmark | GPT-4.5 | o3-pro |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 37.8% | — |
| LiveBench Math | 69.3% | — |
| LMArena Math | 1412 | — |
| MATH Level 5 | 78.6% | — |
Knowledge GPT-4.5 leads
GPT-4.5: 32.4 (#205), o3-pro: 29.0 (#234)
| Benchmark | GPT-4.5 | o3-pro |
|---|---|---|
| Confabulations | 13.6% | 14.2% |
| GPQA Diamond | 68.7% | — |
| Humanity's Last Exam | 5.4% | — |
| Vectara Hallucination Rate | — | 23.3% |
| LMArena Expert | 1394 | — |
Multimodal Not comparable
GPT-4.5: 37.0 (#68), o3-pro: —
| Benchmark | GPT-4.5 | o3-pro |
|---|---|---|
| LMArena Vision | 1195 | — |
| VPCT | 45% | — |
Multilingual Not comparable
GPT-4.5: 52.7 (#78), o3-pro: —
| Benchmark | GPT-4.5 | o3-pro |
|---|---|---|
| LMArena Non-English | 1413 | — |
| LMArena Chinese | 1421 | — |
| LMArena French | 1417 | — |
| LMArena German | 1457 | — |
| LMArena Japanese | 1416 | — |
| LMArena Korean | 1392 | — |
| LMArena Russian | 1419 | — |
Instruction Following Not comparable
GPT-4.5: 72.8 (#129), o3-pro: —
| Benchmark | GPT-4.5 | o3-pro |
|---|---|---|
| LiveBench Instruction Following | 72.3% | — |
| LMArena Instruction Following | 1404 | — |
Long Context o3-pro leads
GPT-4.5: 40.4 (#150), o3-pro: 72.1 (#1)
| Benchmark | GPT-4.5 | o3-pro |
|---|---|---|
| Fiction.LiveBench | 63.9% | 97.2% |
| LMArena Longer Query | 1406 | — |
Writing & Preference Too close to call
GPT-4.5: 57.1 (#129), o3-pro: 57.1 (#128)
| Benchmark | GPT-4.5 | o3-pro |
|---|---|---|
| Short-Story Creative Writing | 75.6% | 84.4% |
| LMArena Text | 1417 | — |
| LMArena Creative Writing | 1394 | — |
| EQ-Bench Creative Writing | 1258 | — |
| LMArena Multi-Turn | 1444 | — |
| LiveBench Language | 61.5% | — |
Frequently asked questions
Is GPT-4.5 better than o3-pro?
o3-pro is the stronger model overall, scoring 42.7 to 36.9 on the Noometry Index.
Is GPT-4.5 or o3-pro better for coding?
o3-pro scores higher on coding benchmarks: 55.1 versus 41.8 in the Noometry coding category.
How many benchmarks do GPT-4.5 and o3-pro share?
8 benchmarks have published results for both models. GPT-4.5 has 42 scored results on Noometry and o3-pro has 12.