Model comparison
GPT-4 Turbo vs GPT-5 Pro
GPT-5 Pro is the stronger model overall, scoring 46.2 to 30.3 on the Noometry Index. GPT-4 Turbo costs 2.8× less per token, which makes it the better buy when GPT-5 Pro's lead doesn't matter for your workload.
Last verified . 4 shared benchmarks.
Summary
- They share 4 benchmarks with published results for both. GPT-4 Turbo scores higher in 0 categories and GPT-5 Pro in 4 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5 Pro leads 48.0 to 8.6.
- The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 0.7% for GPT-4 Turbo and 55.8% for GPT-5 Pro.
- GPT-4 Turbo is cheaper at $10 / $30 per million input/output tokens, against $15 / $120 for GPT-5 Pro.
- GPT-5 Pro accepts more context: 400K tokens versus 128K.
Side by side
| GPT-4 Turbo | GPT-5 Pro | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 30.3 | 46.2 |
| Released | 2023-11-06 | 2025-10-06 |
| Weights | Proprietary | Proprietary |
| Context window | 128K | 400K |
| Max output | 4K | 272K |
| Input $ / M tokens | $10 | $15 |
| Output $ / M tokens | $30 | $120 |
| Results tracked | 36 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5 Pro leads
GPT-4 Turbo: 33.4 (#247), GPT-5 Pro: 43.4 (#77)
| Benchmark | GPT-4 Turbo | GPT-5 Pro |
|---|---|---|
| WeirdML | 18% | 60.4% |
| BigCodeBench Instruct | 48.2% | — |
| LMArena Coding | 1268 | — |
| BigCodeBench Complete | 58.2% | — |
| AlgoTune | — | 1.31 |
| HumanEval+ | 86.6% | — |
| MBPP+ | 73.3% | — |
Agentic & Tool Use Not comparable
GPT-4 Turbo: —, GPT-5 Pro: —
| Benchmark | GPT-4 Turbo | GPT-5 Pro |
|---|---|---|
| METR Time Horizons | 36.7% | — |
Reasoning GPT-5 Pro leads
GPT-4 Turbo: 14.9 (#311), GPT-5 Pro: 39.2 (#52)
| Benchmark | GPT-4 Turbo | GPT-5 Pro |
|---|---|---|
| SimpleBench | 25.1% | 61.6% |
| Epoch Capabilities Index | 127.25 | 150.26 |
| ARC-AGI-2 | — | 18.3% |
| Kagi LLM Benchmark | — | 76.8% |
| ARC-AGI-1 | — | 70.2% |
| Chess Puzzles | 6% | — |
| EnigmaEval | — | 18.8% |
| LMArena Hard Prompts | 1251 | — |
| DTBench | 61.6% | — |
| LMCA | 9.8% | — |
| ForecastBench | 59.4 | — |
Math GPT-5 Pro leads
GPT-4 Turbo: 8.6 (#316), GPT-5 Pro: 48.0 (#53)
| Benchmark | GPT-4 Turbo | GPT-5 Pro |
|---|---|---|
| FrontierMath (Tiers 1-3) | 0.7% | 55.8% |
| FrontierMath Tier 4 | — | 19.5% |
| OTIS Mock AIME 2024-2025 | 6.7% | — |
| LMArena Math | 1272 | — |
| MATH Level 5 | 46.7% | — |
| FrontierMath Tier 4 (v1) | — | 14.6% |
Knowledge GPT-5 Pro leads
GPT-4 Turbo: 24.3 (#263), GPT-5 Pro: 56.2 (#39)
| Benchmark | GPT-4 Turbo | GPT-5 Pro |
|---|---|---|
| GPQA Diamond | 46.6% | — |
| Humanity's Last Exam | — | 31.6% |
| Confabulations | 28.4% | — |
| LMArena Expert | 1223 | — |
| MMLU | 81.3% | — |
Multimodal Not comparable
GPT-4 Turbo: 30.0 (#104), GPT-5 Pro: —
| Benchmark | GPT-4 Turbo | GPT-5 Pro |
|---|---|---|
| LMArena Vision | 1090 | — |
Multilingual Not comparable
GPT-4 Turbo: 40.7 (#211), GPT-5 Pro: —
| Benchmark | GPT-4 Turbo | GPT-5 Pro |
|---|---|---|
| LMArena Non-English | 1245 | — |
| LMArena Chinese | 1242 | — |
| LMArena French | 1275 | — |
| LMArena German | 1259 | — |
| LMArena Japanese | 1194 | — |
| LMArena Korean | 1187 | — |
| LMArena Russian | 1259 | — |
| LMArena Spanish | 1260 | — |
Instruction Following Not comparable
GPT-4 Turbo: 66.0 (#211), GPT-5 Pro: —
| Benchmark | GPT-4 Turbo | GPT-5 Pro |
|---|---|---|
| LMArena Instruction Following | 1250 | — |
Long Context Not comparable
GPT-4 Turbo: 38.0 (#200), GPT-5 Pro: —
| Benchmark | GPT-4 Turbo | GPT-5 Pro |
|---|---|---|
| LMArena Longer Query | 1254 | — |
Writing & Preference Not comparable
GPT-4 Turbo: 47.9 (#201), GPT-5 Pro: —
| Benchmark | GPT-4 Turbo | GPT-5 Pro |
|---|---|---|
| LMArena Text | 1272 | — |
| LMArena Creative Writing | 1269 | — |
| LMArena Multi-Turn | 1267 | — |
Frequently asked questions
Is GPT-4 Turbo better than GPT-5 Pro?
GPT-5 Pro is the stronger model overall, scoring 46.2 to 30.3 on the Noometry Index. GPT-4 Turbo costs 2.8× less per token, which makes it the better buy when GPT-5 Pro's lead doesn't matter for your workload.
Which is cheaper, GPT-4 Turbo or GPT-5 Pro?
GPT-4 Turbo is cheaper. It lists at $10 per million input tokens and $30 per million output tokens; GPT-5 Pro lists at $15 and $120.
Is GPT-4 Turbo or GPT-5 Pro better for coding?
GPT-5 Pro scores higher on coding benchmarks: 43.4 versus 33.4 in the Noometry coding category.
Which has the bigger context window?
GPT-5 Pro does, with 400K tokens against 128K.
How many benchmarks do GPT-4 Turbo and GPT-5 Pro share?
4 benchmarks have published results for both models. GPT-4 Turbo has 36 scored results on Noometry and GPT-5 Pro has 12.