# GPT-5.4 mini vs GPT-5 Pro

> GPT-5 Pro is the stronger model overall, scoring 46.2 to 44.8 on the Noometry Index. GPT-5.4 mini costs 24× 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-mini-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 mini scores higher in 1 category and GPT-5 Pro in 3 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5 Pro leads 39.2 to 30.3.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 37.9% for GPT-5.4 mini and 76.8% for GPT-5 Pro.
- GPT-5.4 mini is cheaper at $0.75 / $4.50 per million input/output tokens, against $15 / $120 for GPT-5 Pro.

## Snapshot

| | GPT-5.4 mini | GPT-5 Pro |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 44.8 | 46.2 |
| Rank | 69 | 58 |
| Context | 400K | 400K |
| Input $/M | $0.75 | $15 |
| Output $/M | $4.50 | $120 |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-5.4 mini: 45.0 (#67)
- GPT-5 Pro: 43.4 (#77)

| Benchmark | GPT-5.4 mini | GPT-5 Pro |
|---|---|---|
| WeirdML | 60.3% | 60.4% |
| FrontierCode | 27% | — |
| LMArena WebDev | 1397 | — |
| SciCode | 49.9% | — |
| LMArena Coding | 1438 | — |
| ALE-Bench | 1,189 | — |
| AlgoTune | — | 1.31 |

## Agentic & Tool Use

- GPT-5.4 mini: 29.6 (#74)
- GPT-5 Pro: —

| Benchmark | GPT-5.4 mini | GPT-5 Pro |
|---|---|---|
| DeepResearch Bench | 36.3% | — |

## Reasoning

- GPT-5.4 mini: 30.3 (#77)
- GPT-5 Pro: 39.2 (#52)

| Benchmark | GPT-5.4 mini | GPT-5 Pro |
|---|---|---|
| ARC-AGI-2 | 18.9% | 18.3% |
| Kagi LLM Benchmark | 37.9% | 76.8% |
| ARC-AGI-1 | 63.7% | 70.2% |
| Epoch Capabilities Index | 148.83 | 150.26 |
| SimpleBench | — | 61.6% |
| NYT Connections (extended) | 61.8% | — |
| CritPt | 10% | — |
| Chess Puzzles | 24% | — |
| EnigmaEval | — | 18.8% |
| Thematic Generalization | 61.7% | — |
| LMArena Hard Prompts | 1424 | — |
| Mystery Game Puzzles | 11% | — |
| DTBench | 80% | — |
| LMCA | 40.8% | — |
| ForecastBench | 57 | — |

## Math

- GPT-5.4 mini: 45.4 (#63)
- GPT-5 Pro: 48.0 (#53)

| Benchmark | GPT-5.4 mini | GPT-5 Pro |
|---|---|---|
| FrontierMath (Tiers 1-3) | 51.2% | 55.8% |
| FrontierMath Tier 4 | 9.8% | 19.5% |
| FrontierMath Tier 4 (v1) | 2.1% | 14.6% |
| OTIS Mock AIME 2024-2025 | 88.9% | — |
| ProofBench | 21% | — |
| LMArena Math | 1418 | — |
| FrontierMath (Feb 2025 set) | 28.3% | — |

## Knowledge

- GPT-5.4 mini: 51.4 (#62)
- GPT-5 Pro: 56.2 (#39)

| Benchmark | GPT-5.4 mini | GPT-5 Pro |
|---|---|---|
| GPQA Diamond | 86.9% | — |
| Humanity's Last Exam | — | 31.6% |
| SimpleQA Verified | 29.4% | — |
| Vectara Hallucination Rate | 5.5% | — |
| LMArena Expert | 1434 | — |

## Multimodal

- GPT-5.4 mini: 39.0 (#51)
- GPT-5 Pro: —

| Benchmark | GPT-5.4 mini | GPT-5 Pro |
|---|---|---|
| LMArena Vision | 1245 | — |

## Multilingual

- GPT-5.4 mini: 52.1 (#94)
- GPT-5 Pro: —

| Benchmark | GPT-5.4 mini | GPT-5 Pro |
|---|---|---|
| LMArena Non-English | 1405 | — |
| LMArena Chinese | 1446 | — |
| LMArena French | 1440 | — |
| LMArena German | 1407 | — |
| LMArena Japanese | 1375 | — |
| LMArena Korean | 1369 | — |
| LMArena Russian | 1417 | — |
| LMArena Spanish | 1403 | — |

## Instruction Following

- GPT-5.4 mini: 74.3 (#99)
- GPT-5 Pro: —

| Benchmark | GPT-5.4 mini | GPT-5 Pro |
|---|---|---|
| LMArena Instruction Following | 1405 | — |

## Long Context

- GPT-5.4 mini: 42.9 (#107)
- GPT-5 Pro: —

| Benchmark | GPT-5.4 mini | GPT-5 Pro |
|---|---|---|
| LMArena Longer Query | 1407 | — |

## Writing & Preference

- GPT-5.4 mini: 64.2 (#56)
- GPT-5 Pro: —

| Benchmark | GPT-5.4 mini | GPT-5 Pro |
|---|---|---|
| LMArena Text | 1411 | — |
| LMArena Creative Writing | 1370 | — |
| EQ-Bench Creative Writing | 1665 | — |
| LMArena Multi-Turn | 1429 | — |

## FAQ

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

GPT-5 Pro is the stronger model overall, scoring 46.2 to 44.8 on the Noometry Index. GPT-5.4 mini costs 24× 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 mini or GPT-5 Pro?

GPT-5.4 mini is cheaper. It lists at $0.75 per million input tokens and $4.50 per million output tokens; GPT-5 Pro lists at $15 and $120.

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

GPT-5.4 mini scores higher on coding benchmarks: 45.0 versus 43.4 in the Noometry coding category.

### Which has the bigger context window?

Both accept 400K tokens.

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

8 benchmarks have published results for both models. GPT-5.4 mini has 46 scored results on Noometry and GPT-5 Pro has 12.