# Grok 3 vs phi-3-medium 14B

> Grok 3 is the stronger model overall, scoring 39.6 to 29.1 on the Noometry Index.

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

## Summary

- They share 3 benchmarks with published results for both. Grok 3 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 Grok 3 leads 46.0 to 9.1.
- The biggest single-benchmark swing is MATH Level 5: 88.7% for Grok 3 and 17.6% for phi-3-medium 14B.
- phi-3-medium 14B has downloadable open weights; the other is API-only.

## Snapshot

| | Grok 3 | phi-3-medium 14B |
|---|---|---|
| Provider | xAI | Microsoft |
| Noometry Index | 39.6 | 29.1 |
| Rank | 150 | 306 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Proprietary | Open |

## Coding

- Grok 3: 41.5 (#113)
- phi-3-medium 14B: 36.3 (#198)

| Benchmark | Grok 3 | phi-3-medium 14B |
|---|---|---|
| Aider Polyglot | 53.3% | — |
| WeirdML | 37.2% | — |
| BigCodeBench Instruct | — | 37.6% |
| LMArena Coding | 1432 | — |
| BigCodeBench Complete | — | 48.7% |

## Agentic & Tool Use

- Grok 3: 30.2 (#69)
- phi-3-medium 14B: —

| Benchmark | Grok 3 | phi-3-medium 14B |
|---|---|---|
| BALROG | 29.5% | — |

## Reasoning

- Grok 3: 13.8 (#322)
- phi-3-medium 14B: —

| Benchmark | Grok 3 | phi-3-medium 14B |
|---|---|---|
| Epoch Capabilities Index | 138.34 | 121.18 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | 36.1% | — |
| Kagi LLM Benchmark | 61.3% | — |
| ARC-AGI-1 | 5.5% | — |
| LMArena Hard Prompts | 1433 | — |
| Adversarial NLI | — | 55.8% |
| BIG-Bench Hard | — | 81.4% |
| HellaSwag | — | 82.4% |
| WinoGrande | — | 81.5% |

## Math

- Grok 3: 36.2 (#122)
- phi-3-medium 14B: 25.2 (#249)

| Benchmark | Grok 3 | phi-3-medium 14B |
|---|---|---|
| MATH Level 5 | 88.7% | 17.6% |
| OTIS Mock AIME 2024-2025 | 55.6% | — |
| Omni-MATH | 46.4% | — |
| LMArena Math | 1390 | — |
| FrontierMath (Feb 2025 set) | 3.8% | — |
| FrontierMath Tier 4 (v1) | 0% | — |

## Knowledge

- Grok 3: 46.0 (#76)
- phi-3-medium 14B: 9.1 (#301)

| Benchmark | Grok 3 | phi-3-medium 14B |
|---|---|---|
| GPQA Diamond | 75.8% | 27.6% |
| MMLU-Pro | 78.8% | — |
| Confabulations | 14.2% | — |
| Vectara Hallucination Rate | 5.8% | — |
| GPQA (HELM) | 65% | — |
| LMArena Expert | 1420 | — |
| ARC (AI2) Challenge | — | 91.6% |
| MMLU | — | 78% |
| OpenBookQA | — | 87.4% |
| TriviaQA | — | 73.9% |

## Multilingual

- Grok 3: 52.5 (#81)
- phi-3-medium 14B: —

| Benchmark | Grok 3 | phi-3-medium 14B |
|---|---|---|
| LMArena Non-English | 1411 | — |
| LMArena Chinese | 1448 | — |
| LMArena French | 1460 | — |
| LMArena German | 1431 | — |
| LMArena Japanese | 1389 | — |
| LMArena Korean | 1374 | — |
| LMArena Russian | 1416 | — |
| LMArena Spanish | 1417 | — |

## Instruction Following

- Grok 3: 75.2 (#69)
- phi-3-medium 14B: —

| Benchmark | Grok 3 | phi-3-medium 14B |
|---|---|---|
| IFEval | 88.4% | — |
| LMArena Instruction Following | 1409 | — |

## Long Context

- Grok 3: 38.7 (#187)
- phi-3-medium 14B: —

| Benchmark | Grok 3 | phi-3-medium 14B |
|---|---|---|
| Fiction.LiveBench | 58.3% | — |
| LMArena Longer Query | 1439 | — |

## Writing & Preference

- Grok 3: 56.0 (#136)
- phi-3-medium 14B: —

| Benchmark | Grok 3 | phi-3-medium 14B |
|---|---|---|
| LMArena Text | 1426 | — |
| LMArena Creative Writing | 1414 | — |
| Short-Story Creative Writing | 76.4% | — |
| EQ-Bench Creative Writing | 1186 | — |
| WildBench | 84.9% | — |
| LMArena Multi-Turn | 1424 | — |

## FAQ

### Is Grok 3 better than phi-3-medium 14B?

Grok 3 is the stronger model overall, scoring 39.6 to 29.1 on the Noometry Index.

### Is Grok 3 or phi-3-medium 14B better for coding?

Grok 3 scores higher on coding benchmarks: 41.5 versus 36.3 in the Noometry coding category.

### How many benchmarks do Grok 3 and phi-3-medium 14B share?

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