# GPT-4.1 nano vs phi-3-medium 14B

> phi-3-medium 14B is the stronger model overall, scoring 29.1 to 27.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-4-1-nano-vs-phi-3-medium-14b
- Last updated: 2026-10-10
- Shared benchmarks: 3

## Summary

- They share 3 benchmarks with published results for both. GPT-4.1 nano scores higher in 2 categories and phi-3-medium 14B in 1 category; 2 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-4.1 nano leads 21.8 to 9.1.
- The biggest single-benchmark swing is MATH Level 5: 70% for GPT-4.1 nano and 17.6% for phi-3-medium 14B.
- phi-3-medium 14B has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-4.1 nano | phi-3-medium 14B |
|---|---|---|
| Provider | OpenAI | Microsoft |
| Noometry Index | 27.7 | 29.1 |
| Rank | 322 | 306 |
| Context | 1.05M | — |
| Input $/M | $0.10 | — |
| Output $/M | $0.40 | — |
| Weights | Proprietary | Open |

## Coding

- GPT-4.1 nano: 23.8 (#325)
- phi-3-medium 14B: 36.3 (#198)

| Benchmark | GPT-4.1 nano | phi-3-medium 14B |
|---|---|---|
| Aider Polyglot | 8.9% | — |
| SciCode | 25.9% | — |
| WeirdML | 19% | — |
| BigCodeBench Instruct | — | 37.6% |
| LMArena Coding | 1306 | — |
| BigCodeBench Complete | — | 48.7% |

## Agentic & Tool Use

- GPT-4.1 nano: 26.3 (#98)
- phi-3-medium 14B: —

| Benchmark | GPT-4.1 nano | phi-3-medium 14B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 33% | — |

## Reasoning

- GPT-4.1 nano: 8.6 (#344)
- phi-3-medium 14B: —

| Benchmark | GPT-4.1 nano | phi-3-medium 14B |
|---|---|---|
| Epoch Capabilities Index | 129.62 | 121.18 |
| ARC-AGI-2 | 0% | — |
| Kagi LLM Benchmark | 33.3% | — |
| ARC-AGI-1 | 0% | — |
| CritPt | 0% | — |
| LMArena Hard Prompts | 1286 | — |
| DTBench | 52.5% | — |
| LMCA | 5.5% | — |
| Adversarial NLI | — | 55.8% |
| BIG-Bench Hard | — | 81.4% |
| HellaSwag | — | 82.4% |
| WinoGrande | — | 81.5% |

## Math

- GPT-4.1 nano: 25.5 (#246)
- phi-3-medium 14B: 25.2 (#249)

| Benchmark | GPT-4.1 nano | phi-3-medium 14B |
|---|---|---|
| MATH Level 5 | 70% | 17.6% |
| OTIS Mock AIME 2024-2025 | 28.9% | — |
| Omni-MATH | 36.7% | — |
| LMArena Math | 1274 | — |
| FrontierMath (Feb 2025 set) | 1% | — |

## Knowledge

- GPT-4.1 nano: 21.8 (#268)
- phi-3-medium 14B: 9.1 (#301)

| Benchmark | GPT-4.1 nano | phi-3-medium 14B |
|---|---|---|
| GPQA Diamond | 48.9% | 27.6% |
| SimpleQA Verified | 6% | — |
| MMLU-Pro | 55% | — |
| GPQA (HELM) | 50.7% | — |
| LMArena Expert | 1272 | — |
| ARC (AI2) Challenge | — | 91.6% |
| MMLU | — | 78% |
| OpenBookQA | — | 87.4% |
| TriviaQA | — | 73.9% |

## Multimodal

- GPT-4.1 nano: 28.6 (#108)
- phi-3-medium 14B: —

| Benchmark | GPT-4.1 nano | phi-3-medium 14B |
|---|---|---|
| LMArena Vision | 1063 | — |

## Multilingual

- GPT-4.1 nano: 41.8 (#200)
- phi-3-medium 14B: —

| Benchmark | GPT-4.1 nano | phi-3-medium 14B |
|---|---|---|
| LMArena Non-English | 1260 | — |
| LMArena Chinese | 1270 | — |
| LMArena German | 1288 | — |
| LMArena Japanese | 1199 | — |
| LMArena Russian | 1261 | — |

## Instruction Following

- GPT-4.1 nano: 68.0 (#188)
- phi-3-medium 14B: —

| Benchmark | GPT-4.1 nano | phi-3-medium 14B |
|---|---|---|
| IFEval | 84.3% | — |
| LMArena Instruction Following | 1267 | — |

## Long Context

- GPT-4.1 nano: 23.7 (#291)
- phi-3-medium 14B: —

| Benchmark | GPT-4.1 nano | phi-3-medium 14B |
|---|---|---|
| Fiction.LiveBench | 25% | — |
| LMArena Longer Query | 1283 | — |

## Writing & Preference

- GPT-4.1 nano: 40.7 (#238)
- phi-3-medium 14B: —

| Benchmark | GPT-4.1 nano | phi-3-medium 14B |
|---|---|---|
| LMArena Text | 1285 | — |
| LMArena Creative Writing | 1260 | — |
| EQ-Bench Creative Writing | 946 | — |
| WildBench | 81.2% | — |
| LMArena Multi-Turn | 1277 | — |

## FAQ

### Is GPT-4.1 nano better than phi-3-medium 14B?

phi-3-medium 14B is the stronger model overall, scoring 29.1 to 27.7 on the Noometry Index.

### Is GPT-4.1 nano or phi-3-medium 14B better for coding?

phi-3-medium 14B scores higher on coding benchmarks: 36.3 versus 23.8 in the Noometry coding category.

### How many benchmarks do GPT-4.1 nano and phi-3-medium 14B share?

3 benchmarks have published results for both models. GPT-4.1 nano has 38 scored results on Noometry and phi-3-medium 14B has 13.