# GPT-5.4 nano vs GPT-5 Pro

> GPT-5 Pro is the stronger model overall, scoring 46.4 to 41.9 on the Noometry Index. GPT-5.4 nano costs 89× less per token, which makes it the better buy when GPT-5 Pro's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gpt-5-4-nano-vs-gpt-5-pro
- Last updated: 2026-10-10
- Shared benchmarks: 8

## Summary

- They share 8 benchmarks with published results for both. GPT-5.4 nano scores higher in 0 categories and GPT-5 Pro in 4 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5 Pro leads 38.9 to 23.7.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 39.7% for GPT-5.4 nano and 76.8% for GPT-5 Pro.
- GPT-5.4 nano is cheaper at $0.20 / $1.25 per million input/output tokens, against $15 / $120 for GPT-5 Pro.

## Snapshot

| | GPT-5.4 nano | GPT-5 Pro |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 41.9 | 46.4 |
| Rank | 125 | 64 |
| Context | 400K | 400K |
| Input $/M | $0.20 | $15 |
| Output $/M | $1.25 | $120 |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-5.4 nano: 43.6 (#84)
- GPT-5 Pro: 44.0 (#80)

| Benchmark | GPT-5.4 nano | GPT-5 Pro |
|---|---|---|
| WeirdML | 49.2% | 60.4% |
| SciCode | 46.9% | — |
| LMArena Coding | 1405 | — |
| ALE-Bench | 1,005 | — |
| AlgoTune | — | 1.31 |

## Reasoning

- GPT-5.4 nano: 23.7 (#173)
- GPT-5 Pro: 38.9 (#62)

| Benchmark | GPT-5.4 nano | GPT-5 Pro |
|---|---|---|
| ARC-AGI-2 | 5.7% | 18.3% |
| Kagi LLM Benchmark | 39.7% | 76.8% |
| ARC-AGI-1 | 51.5% | 70.2% |
| Epoch Capabilities Index | 145.81 | 150.28 |
| SimpleBench | — | 61.6% |
| CritPt | 9.3% | — |
| Chess Puzzles | 30% | — |
| EnigmaEval | — | 18.8% |
| LMArena Hard Prompts | 1381 | — |
| Mystery Game Puzzles | 9% | — |
| DTBench | 80.3% | — |
| LMCA | 36.9% | — |
| ForecastBench | 57.3 | — |

## Math

- GPT-5.4 nano: 40.9 (#88)
- GPT-5 Pro: 48.5 (#63)

| Benchmark | GPT-5.4 nano | GPT-5 Pro |
|---|---|---|
| FrontierMath (Tiers 1-3) | 44.9% | 55.8% |
| FrontierMath Tier 4 | 12.2% | 19.5% |
| FrontierMath Tier 4 (v1) | 6.3% | 14.6% |
| OTIS Mock AIME 2024-2025 | 87.8% | — |
| ProofBench | 5% | — |
| LMArena Math | 1406 | — |
| FrontierMath (Feb 2025 set) | 25.9% | — |

## Knowledge

- GPT-5.4 nano: 41.9 (#103)
- GPT-5 Pro: 56.7 (#42)

| Benchmark | GPT-5.4 nano | GPT-5 Pro |
|---|---|---|
| GPQA Diamond | 78.5% | — |
| Humanity's Last Exam | — | 31.6% |
| SimpleQA Verified | 11.7% | — |
| Vectara Hallucination Rate | 3.1% | — |
| LMArena Expert | 1396 | — |

## Multimodal

- GPT-5.4 nano: 36.7 (#78)
- GPT-5 Pro: —

| Benchmark | GPT-5.4 nano | GPT-5 Pro |
|---|---|---|
| LMArena Vision | 1196 | — |

## Multilingual

- GPT-5.4 nano: 48.6 (#140)
- GPT-5 Pro: —

| Benchmark | GPT-5.4 nano | GPT-5 Pro |
|---|---|---|
| LMArena Non-English | 1359 | — |
| LMArena Chinese | 1392 | — |
| LMArena French | 1396 | — |
| LMArena German | 1367 | — |
| LMArena Japanese | 1343 | — |
| LMArena Korean | 1320 | — |
| LMArena Russian | 1363 | — |
| LMArena Spanish | 1371 | — |

## Instruction Following

- GPT-5.4 nano: 71.9 (#144)
- GPT-5 Pro: —

| Benchmark | GPT-5.4 nano | GPT-5 Pro |
|---|---|---|
| LMArena Instruction Following | 1362 | — |

## Long Context

- GPT-5.4 nano: 41.6 (#137)
- GPT-5 Pro: —

| Benchmark | GPT-5.4 nano | GPT-5 Pro |
|---|---|---|
| LMArena Longer Query | 1366 | — |

## Writing & Preference

- GPT-5.4 nano: 55.7 (#142)
- GPT-5 Pro: —

| Benchmark | GPT-5.4 nano | GPT-5 Pro |
|---|---|---|
| LMArena Text | 1372 | — |
| LMArena Creative Writing | 1314 | — |
| LMArena Multi-Turn | 1382 | — |

## FAQ

### Is GPT-5.4 nano better than GPT-5 Pro?

GPT-5 Pro is the stronger model overall, scoring 46.4 to 41.9 on the Noometry Index. GPT-5.4 nano costs 89× 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-5.4 nano or GPT-5 Pro?

GPT-5.4 nano is cheaper. It lists at $0.20 per million input tokens and $1.25 per million output tokens; GPT-5 Pro lists at $15 and $120.

### Is GPT-5.4 nano or GPT-5 Pro better for coding?

They score almost the same on coding (43.6 vs 44.0); test both on your own repository before choosing.

### Which has the bigger context window?

Both accept 400K tokens.

### How many benchmarks do GPT-5.4 nano and GPT-5 Pro share?

8 benchmarks have published results for both models. GPT-5.4 nano has 40 scored results on Noometry and GPT-5 Pro has 12.