Model comparison
GPT-4 Turbo vs o3-pro
o3-pro is the stronger model overall, scoring 42.9 to 30.5 on the Noometry Index. GPT-4 Turbo costs 2.3× less per token, which makes it the better buy when o3-pro's lead doesn't matter for your workload.
Last verified . 5 shared benchmarks.
Summary
- They share 5 benchmarks with published results for both. GPT-4 Turbo scores higher in 0 categories and o3-pro in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in long context, where o3-pro leads 72.2 to 38.0.
- The biggest single-benchmark swing is WeirdML: 18% for GPT-4 Turbo and 58.2% for o3-pro.
- GPT-4 Turbo is cheaper at $10 / $30 per million input/output tokens, against $20 / $80 for o3-pro.
- o3-pro accepts more context: 200K tokens versus 128K.
Side by side
| GPT-4 Turbo | o3-pro | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 30.5 | 42.9 |
| Released | 2023-11-06 | 2025-06-10 |
| Weights | Proprietary | Proprietary |
| Context window | 128K | 200K |
| Max output | 4K | 100K |
| Input $ / M tokens | $10 | $20 |
| Output $ / M tokens | $30 | $80 |
| Results tracked | 36 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3-pro leads
GPT-4 Turbo: 33.8 (#249), o3-pro: 55.5 (#24)
| Benchmark | GPT-4 Turbo | o3-pro |
|---|---|---|
| WeirdML | 18% | 58.2% |
| Aider Polyglot | — | 84.9% |
| BigCodeBench Instruct | 48.2% | — |
| LMArena Coding | 1268 | — |
| BigCodeBench Complete | 58.2% | — |
| HumanEval+ | 86.6% | — |
| MBPP+ | 73.3% | — |
Agentic & Tool Use Not comparable
GPT-4 Turbo: —, o3-pro: —
| Benchmark | GPT-4 Turbo | o3-pro |
|---|---|---|
| METR Time Horizons | 36.7% | — |
Reasoning o3-pro leads
GPT-4 Turbo: 15.3 (#317), o3-pro: 23.8 (#171)
| Benchmark | GPT-4 Turbo | o3-pro |
|---|---|---|
| DTBench | 61.6% | 86.9% |
| LMCA | 9.8% | 38.5% |
| Epoch Capabilities Index | 127.25 | 147.42 |
| ARC-AGI-2 | — | 4.9% |
| SimpleBench | 25.1% | — |
| Kagi LLM Benchmark | — | 72.1% |
| ARC-AGI-1 | — | 59.3% |
| Chess Puzzles | 6% | — |
| LMArena Hard Prompts | 1251 | — |
| ForecastBench | 59.4 | — |
Math Not comparable
GPT-4 Turbo: 9.0 (#322), o3-pro: —
| Benchmark | GPT-4 Turbo | o3-pro |
|---|---|---|
| FrontierMath (Tiers 1-3) | 0.7% | — |
| OTIS Mock AIME 2024-2025 | 6.7% | — |
| LMArena Math | 1272 | — |
| MATH Level 5 | 46.7% | — |
Knowledge o3-pro leads
GPT-4 Turbo: 24.3 (#268), o3-pro: 29.5 (#238)
| Benchmark | GPT-4 Turbo | o3-pro |
|---|---|---|
| Confabulations | 28.4% | 14.2% |
| GPQA Diamond | 46.6% | — |
| Vectara Hallucination Rate | — | 23.3% |
| LMArena Expert | 1223 | — |
| MMLU | 81.3% | — |
Multimodal Not comparable
GPT-4 Turbo: 30.6 (#110), o3-pro: —
| Benchmark | GPT-4 Turbo | o3-pro |
|---|---|---|
| LMArena Vision | 1090 | — |
Multilingual Not comparable
GPT-4 Turbo: 40.5 (#216), o3-pro: —
| Benchmark | GPT-4 Turbo | o3-pro |
|---|---|---|
| LMArena Non-English | 1245 | — |
| LMArena Chinese | 1242 | — |
| LMArena French | 1276 | — |
| LMArena German | 1259 | — |
| LMArena Japanese | 1194 | — |
| LMArena Korean | 1187 | — |
| LMArena Russian | 1259 | — |
| LMArena Spanish | 1260 | — |
Instruction Following Not comparable
GPT-4 Turbo: 65.8 (#216), o3-pro: —
| Benchmark | GPT-4 Turbo | o3-pro |
|---|---|---|
| LMArena Instruction Following | 1249 | — |
Long Context o3-pro leads
GPT-4 Turbo: 38.0 (#206), o3-pro: 72.2 (#1)
| Benchmark | GPT-4 Turbo | o3-pro |
|---|---|---|
| Fiction.LiveBench | — | 97.2% |
| LMArena Longer Query | 1254 | — |
Writing & Preference o3-pro leads
GPT-4 Turbo: 47.7 (#206), o3-pro: 57.1 (#133)
| Benchmark | GPT-4 Turbo | o3-pro |
|---|---|---|
| LMArena Text | 1272 | — |
| LMArena Creative Writing | 1269 | — |
| Short-Story Creative Writing | — | 84.4% |
| LMArena Multi-Turn | 1267 | — |
Frequently asked questions
Is GPT-4 Turbo better than o3-pro?
o3-pro is the stronger model overall, scoring 42.9 to 30.5 on the Noometry Index. GPT-4 Turbo costs 2.3× less per token, which makes it the better buy when o3-pro's lead doesn't matter for your workload.
Which is cheaper, GPT-4 Turbo or o3-pro?
GPT-4 Turbo is cheaper. It lists at $10 per million input tokens and $30 per million output tokens; o3-pro lists at $20 and $80.
Is GPT-4 Turbo or o3-pro better for coding?
o3-pro scores higher on coding benchmarks: 55.5 versus 33.8 in the Noometry coding category.
Which has the bigger context window?
o3-pro does, with 200K tokens against 128K.
How many benchmarks do GPT-4 Turbo and o3-pro share?
5 benchmarks have published results for both models. GPT-4 Turbo has 36 scored results on Noometry and o3-pro has 12.