Model comparison
GPT-4 vs o1-pro
o1-pro is the stronger model overall, scoring 31.5 to 29.1 on the Noometry Index. GPT-4 costs 7.0× less per token, which makes it the better buy when o1-pro's lead doesn't matter for your workload.
Last verified . 0 shared benchmarks.
Summary
- The widest gap is in knowledge, where o1-pro leads 29.7 to 18.4.
- GPT-4 is cheaper at $30 / $60 per million input/output tokens, against $150 / $600 for o1-pro.
- o1-pro accepts more context: 200K tokens versus 8K.
Side by side
| GPT-4 | o1-pro | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 29.1 | 31.5 |
| Released | 2023-03-14 | 2025-03-19 |
| Weights | Proprietary | Proprietary |
| Context window | 8K | 200K |
| Max output | 8K | 100K |
| Input $ / M tokens | $30 | $150 |
| Output $ / M tokens | $60 | $600 |
| Results tracked | 38 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
GPT-4: 31.6 (#283), o1-pro: —
| Benchmark | GPT-4 | o1-pro |
|---|---|---|
| WeirdML | 12.4% | — |
| BigCodeBench Instruct | 46% | — |
| LMArena Coding | 1254 | — |
| BigCodeBench Complete | 57.2% | — |
| HumanEval+ | 79.3% | — |
Agentic & Tool Use Not comparable
GPT-4: —, o1-pro: —
| Benchmark | GPT-4 | o1-pro |
|---|---|---|
| METR Time Horizons | 36.1% | — |
Reasoning o1-pro leads
GPT-4: 17.8 (#289), o1-pro: 20.4 (#239)
| Benchmark | GPT-4 | o1-pro |
|---|---|---|
| ARC-AGI-1 | — | 23.3% |
| Chess Puzzles | 4% | — |
| EnigmaEval | — | 6.1% |
| LMArena Hard Prompts | 1241 | — |
| Mystery Game Puzzles | 12% | — |
| DTBench | 62.7% | — |
| LMCA | 17.1% | — |
| BIG-Bench Hard | 75.1% | — |
| Epoch Capabilities Index | 125.89 | — |
| ForecastBench | 57.8 | — |
| HellaSwag | 95.3% | — |
| WinoGrande | 87.5% | — |
Math Not comparable
GPT-4: 10.8 (#309), o1-pro: —
| Benchmark | GPT-4 | o1-pro |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.1% | — |
| LMArena Math | 1269 | — |
| MATH Level 5 | 23% | — |
| GSM8K | 92% | — |
Knowledge o1-pro leads
GPT-4: 18.4 (#282), o1-pro: 29.7 (#234)
| Benchmark | GPT-4 | o1-pro |
|---|---|---|
| GPQA Diamond | 35.7% | — |
| Humanity's Last Exam | — | 8.1% |
| LMArena Expert | 1211 | — |
| MMLU | 86.4% | — |
| TriviaQA | 84.8% | — |
Multilingual Not comparable
GPT-4: 40.6 (#215), o1-pro: —
| Benchmark | GPT-4 | o1-pro |
|---|---|---|
| LMArena Non-English | 1246 | — |
| LMArena Chinese | 1242 | — |
| LMArena French | 1283 | — |
| LMArena German | 1251 | — |
| LMArena Japanese | 1209 | — |
| LMArena Korean | 1184 | — |
| LMArena Russian | 1251 | — |
| LMArena Spanish | 1261 | — |
Instruction Following Not comparable
GPT-4: 65.3 (#222), o1-pro: —
| Benchmark | GPT-4 | o1-pro |
|---|---|---|
| LMArena Instruction Following | 1241 | — |
Long Context Not comparable
GPT-4: 37.7 (#212), o1-pro: —
| Benchmark | GPT-4 | o1-pro |
|---|---|---|
| LMArena Longer Query | 1244 | — |
Writing & Preference Not comparable
GPT-4: 34.9 (#268), o1-pro: —
| Benchmark | GPT-4 | o1-pro |
|---|---|---|
| LMArena Text | 1263 | — |
| LMArena Creative Writing | 1244 | — |
| EQ-Bench Creative Writing | 752 | — |
| LMArena Multi-Turn | 1257 | — |
Frequently asked questions
Is GPT-4 better than o1-pro?
o1-pro is the stronger model overall, scoring 31.5 to 29.1 on the Noometry Index. GPT-4 costs 7.0× less per token, which makes it the better buy when o1-pro's lead doesn't matter for your workload.
Which is cheaper, GPT-4 or o1-pro?
GPT-4 is cheaper. It lists at $30 per million input tokens and $60 per million output tokens; o1-pro lists at $150 and $600.
Which has the bigger context window?
o1-pro does, with 200K tokens against 8K.
How many benchmarks do GPT-4 and o1-pro share?
0 benchmarks have published results for both models. GPT-4 has 38 scored results on Noometry and o1-pro has 3.