Model comparison
GPT-5 Nano vs GPT-5 Pro
GPT-5 Pro is the stronger model overall, scoring 46.4 to 33.5 on the Noometry Index. GPT-5 Nano costs 300× less per token, which makes it the better buy when GPT-5 Pro's lead doesn't matter for your workload.
Last verified . 8 shared benchmarks.
Summary
- They share 8 benchmarks with published results for both. GPT-5 Nano scores higher in 0 categories and GPT-5 Pro in 4 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5 Pro leads 38.9 to 16.3.
- The biggest single-benchmark swing is ARC-AGI-1: 20.7% for GPT-5 Nano and 70.2% for GPT-5 Pro.
- GPT-5 Nano is cheaper at $0.05 / $0.40 per million input/output tokens, against $15 / $120 for GPT-5 Pro.
Side by side
| GPT-5 Nano | GPT-5 Pro | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 33.5 | 46.4 |
| Released | 2025-08-07 | 2025-10-06 |
| Weights | Proprietary | Proprietary |
| Context window | 400K | 400K |
| Max output | 128K | 272K |
| Input $ / M tokens | $0.05 | $15 |
| Output $ / M tokens | $0.40 | $120 |
| Results tracked | 49 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5 Pro leads
GPT-5 Nano: 33.6 (#254), GPT-5 Pro: 44.0 (#80)
| Benchmark | GPT-5 Nano | GPT-5 Pro |
|---|---|---|
| WeirdML | 38.1% | 60.4% |
| SWE-bench Verified (bash only) | 34.8% | — |
| LMArena Coding | 1351 | — |
| ALE-Bench | 718.67 | — |
| AlgoTune | — | 1.31 |
Agentic & Tool Use Not comparable
GPT-5 Nano: 25.8 (#106), GPT-5 Pro: —
| Benchmark | GPT-5 Nano | GPT-5 Pro |
|---|---|---|
| Terminal-Bench | 21.8% | — |
| Berkeley Function Calling Leaderboard | 51.5% | — |
Reasoning GPT-5 Pro leads
GPT-5 Nano: 16.3 (#306), GPT-5 Pro: 38.9 (#62)
| Benchmark | GPT-5 Nano | GPT-5 Pro |
|---|---|---|
| ARC-AGI-2 | 2.6% | 18.3% |
| Kagi LLM Benchmark | 62.2% | 76.8% |
| ARC-AGI-1 | 20.7% | 70.2% |
| Epoch Capabilities Index | 139.38 | 150.28 |
| SimpleBench | — | 61.6% |
| Chess Puzzles | 27% | — |
| EnigmaEval | — | 18.8% |
| LMArena Hard Prompts | 1328 | — |
| Mystery Game Puzzles | 9% | — |
| DTBench | 62.7% | — |
| LMCA | 7.9% | — |
| ForecastBench | 59.1 | — |
Math GPT-5 Pro leads
GPT-5 Nano: 29.4 (#241), GPT-5 Pro: 48.5 (#63)
| Benchmark | GPT-5 Nano | GPT-5 Pro |
|---|---|---|
| FrontierMath (Tiers 1-3) | 20% | 55.8% |
| FrontierMath Tier 4 | 2.4% | 19.5% |
| FrontierMath Tier 4 (v1) | 2.1% | 14.6% |
| OTIS Mock AIME 2024-2025 | 81.1% | — |
| ProofBench | 12% | — |
| Omni-MATH | 54.6% | — |
| LMArena Math | 1317 | — |
| MATH Level 5 | 95.2% | — |
| FrontierMath (Feb 2025 set) | 8.3% | — |
Knowledge GPT-5 Pro leads
GPT-5 Nano: 35.9 (#178), GPT-5 Pro: 56.7 (#42)
| Benchmark | GPT-5 Nano | GPT-5 Pro |
|---|---|---|
| GPQA Diamond | 69.4% | — |
| Humanity's Last Exam | — | 31.6% |
| SimpleQA Verified | 11.7% | — |
| MMLU-Pro | 77.8% | — |
| Vectara Hallucination Rate | 10.5% | — |
| GPQA (HELM) | 67.9% | — |
| LMArena Expert | 1321 | — |
Multimodal Not comparable
GPT-5 Nano: 31.3 (#108), GPT-5 Pro: —
| Benchmark | GPT-5 Nano | GPT-5 Pro |
|---|---|---|
| LMArena Vision | 1159 | — |
| VPCT | 37.2% | — |
Multilingual Not comparable
GPT-5 Nano: 45.3 (#172), GPT-5 Pro: —
| Benchmark | GPT-5 Nano | GPT-5 Pro |
|---|---|---|
| LMArena Non-English | 1313 | — |
| LMArena Chinese | 1356 | — |
| LMArena German | 1327 | — |
| LMArena Japanese | 1226 | — |
| LMArena Korean | 1269 | — |
| LMArena Russian | 1296 | — |
| LMArena Spanish | 1360 | — |
Instruction Following Not comparable
GPT-5 Nano: 75.0 (#79), GPT-5 Pro: —
| Benchmark | GPT-5 Nano | GPT-5 Pro |
|---|---|---|
| IFEval | 93.2% | — |
| LMArena Instruction Following | 1306 | — |
Long Context Not comparable
GPT-5 Nano: 31.3 (#281), GPT-5 Pro: —
| Benchmark | GPT-5 Nano | GPT-5 Pro |
|---|---|---|
| Fiction.LiveBench | 44.4% | — |
| LMArena Longer Query | 1312 | — |
Writing & Preference Not comparable
GPT-5 Nano: 39.1 (#249), GPT-5 Pro: —
| Benchmark | GPT-5 Nano | GPT-5 Pro |
|---|---|---|
| LMArena Text | 1320 | — |
| LMArena Creative Writing | 1249 | — |
| EQ-Bench Creative Writing | 705 | — |
| WildBench | 80.6% | — |
| LMArena Multi-Turn | 1311 | — |
Frequently asked questions
Is GPT-5 Nano better than GPT-5 Pro?
GPT-5 Pro is the stronger model overall, scoring 46.4 to 33.5 on the Noometry Index. GPT-5 Nano costs 300× 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-5 Nano or GPT-5 Pro?
GPT-5 Nano is cheaper. It lists at $0.05 per million input tokens and $0.40 per million output tokens; GPT-5 Pro lists at $15 and $120.
Is GPT-5 Nano or GPT-5 Pro better for coding?
GPT-5 Pro scores higher on coding benchmarks: 44.0 versus 33.6 in the Noometry coding category.
Which has the bigger context window?
Both accept 400K tokens.
How many benchmarks do GPT-5 Nano and GPT-5 Pro share?
8 benchmarks have published results for both models. GPT-5 Nano has 49 scored results on Noometry and GPT-5 Pro has 12.