# GPT-5.4 nano vs phi-3-medium 14B

> GPT-5.4 nano is the stronger model overall, scoring 41.9 to 29.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-5-4-nano-vs-phi-3-medium-14b
- Last updated: 2026-10-10
- Shared benchmarks: 2

## Summary

- They share 2 benchmarks with published results for both. GPT-5.4 nano scores higher in 3 categories and phi-3-medium 14B in 0 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-5.4 nano leads 41.8 to 9.1.
- The biggest single-benchmark swing is GPQA Diamond: 78.5% for GPT-5.4 nano and 27.6% for phi-3-medium 14B.
- phi-3-medium 14B has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-5.4 nano | phi-3-medium 14B |
|---|---|---|
| Provider | OpenAI | Microsoft |
| Noometry Index | 41.9 | 29.1 |
| Rank | 111 | 306 |
| Context | 400K | — |
| Input $/M | $0.20 | — |
| Output $/M | $1.25 | — |
| Weights | Proprietary | Open |

## Coding

- GPT-5.4 nano: 43.1 (#82)
- phi-3-medium 14B: 36.3 (#198)

| Benchmark | GPT-5.4 nano | phi-3-medium 14B |
|---|---|---|
| SciCode | 46.9% | — |
| WeirdML | 49.2% | — |
| BigCodeBench Instruct | — | 37.6% |
| LMArena Coding | 1404 | — |
| BigCodeBench Complete | — | 48.7% |
| ALE-Bench | 1,005 | — |

## Reasoning

- GPT-5.4 nano: 23.8 (#159)
- phi-3-medium 14B: —

| Benchmark | GPT-5.4 nano | phi-3-medium 14B |
|---|---|---|
| Epoch Capabilities Index | 145.78 | 121.18 |
| ARC-AGI-2 | 5.7% | — |
| Kagi LLM Benchmark | 39.7% | — |
| ARC-AGI-1 | 51.5% | — |
| CritPt | 9.3% | — |
| Chess Puzzles | 30% | — |
| LMArena Hard Prompts | 1380 | — |
| Mystery Game Puzzles | 9% | — |
| DTBench | 80.3% | — |
| LMCA | 36.9% | — |
| Adversarial NLI | — | 55.8% |
| BIG-Bench Hard | — | 81.4% |
| ForecastBench | 57.3 | — |
| HellaSwag | — | 82.4% |
| WinoGrande | — | 81.5% |

## Math

- GPT-5.4 nano: 40.7 (#76)
- phi-3-medium 14B: 25.2 (#249)

| Benchmark | GPT-5.4 nano | phi-3-medium 14B |
|---|---|---|
| FrontierMath (Tiers 1-3) | 44.9% | — |
| FrontierMath Tier 4 | 12.2% | — |
| OTIS Mock AIME 2024-2025 | 87.8% | — |
| ProofBench | 5% | — |
| LMArena Math | 1406 | — |
| MATH Level 5 | — | 17.6% |
| FrontierMath (Feb 2025 set) | 25.9% | — |
| FrontierMath Tier 4 (v1) | 6.3% | — |

## Knowledge

- GPT-5.4 nano: 41.8 (#94)
- phi-3-medium 14B: 9.1 (#301)

| Benchmark | GPT-5.4 nano | phi-3-medium 14B |
|---|---|---|
| GPQA Diamond | 78.5% | 27.6% |
| SimpleQA Verified | 11.7% | — |
| Vectara Hallucination Rate | 3.1% | — |
| LMArena Expert | 1397 | — |
| ARC (AI2) Challenge | — | 91.6% |
| MMLU | — | 78% |
| OpenBookQA | — | 87.4% |
| TriviaQA | — | 73.9% |

## Multimodal

- GPT-5.4 nano: 36.0 (#73)
- phi-3-medium 14B: —

| Benchmark | GPT-5.4 nano | phi-3-medium 14B |
|---|---|---|
| LMArena Vision | 1196 | — |

## Multilingual

- GPT-5.4 nano: 48.8 (#136)
- phi-3-medium 14B: —

| Benchmark | GPT-5.4 nano | phi-3-medium 14B |
|---|---|---|
| LMArena Non-English | 1359 | — |
| LMArena Chinese | 1391 | — |
| LMArena French | 1396 | — |
| LMArena German | 1368 | — |
| LMArena Japanese | 1342 | — |
| LMArena Korean | 1321 | — |
| LMArena Russian | 1363 | — |
| LMArena Spanish | 1368 | — |

## Instruction Following

- GPT-5.4 nano: 72.1 (#139)
- phi-3-medium 14B: —

| Benchmark | GPT-5.4 nano | phi-3-medium 14B |
|---|---|---|
| LMArena Instruction Following | 1362 | — |

## Long Context

- GPT-5.4 nano: 41.6 (#131)
- phi-3-medium 14B: —

| Benchmark | GPT-5.4 nano | phi-3-medium 14B |
|---|---|---|
| LMArena Longer Query | 1365 | — |

## Writing & Preference

- GPT-5.4 nano: 55.9 (#137)
- phi-3-medium 14B: —

| Benchmark | GPT-5.4 nano | phi-3-medium 14B |
|---|---|---|
| LMArena Text | 1372 | — |
| LMArena Creative Writing | 1313 | — |
| LMArena Multi-Turn | 1382 | — |

## FAQ

### Is GPT-5.4 nano better than phi-3-medium 14B?

GPT-5.4 nano is the stronger model overall, scoring 41.9 to 29.1 on the Noometry Index.

### Is GPT-5.4 nano or phi-3-medium 14B better for coding?

GPT-5.4 nano scores higher on coding benchmarks: 43.1 versus 36.3 in the Noometry coding category.

### How many benchmarks do GPT-5.4 nano and phi-3-medium 14B share?

2 benchmarks have published results for both models. GPT-5.4 nano has 40 scored results on Noometry and phi-3-medium 14B has 13.