# phi-3-medium 14B vs Step 2 16k Exp 202412

> Step 2 16k Exp 202412 is the stronger model overall, scoring 38.6 to 29.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/phi-3-medium-14b-vs-step-2-16k-exp-202412
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in knowledge, where Step 2 16k Exp 202412 leads 34.6 to 9.1.
- phi-3-medium 14B has downloadable open weights; the other is API-only.

## Snapshot

| | phi-3-medium 14B | Step 2 16k Exp 202412 |
|---|---|---|
| Provider | Microsoft | StepFun |
| Noometry Index | 29.1 | 38.6 |
| Rank | 306 | 173 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Proprietary |

## Coding

- phi-3-medium 14B: 36.3 (#198)
- Step 2 16k Exp 202412: 37.9 (#170)

| Benchmark | phi-3-medium 14B | Step 2 16k Exp 202412 |
|---|---|---|
| BigCodeBench Instruct | 37.6% | — |
| LMArena Coding | — | 1316 |
| BigCodeBench Complete | 48.7% | — |

## Reasoning

- phi-3-medium 14B: —
- Step 2 16k Exp 202412: 24.8 (#140)

| Benchmark | phi-3-medium 14B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Hard Prompts | — | 1299 |
| Adversarial NLI | 55.8% | — |
| BIG-Bench Hard | 81.4% | — |
| Epoch Capabilities Index | 121.18 | — |
| HellaSwag | 82.4% | — |
| WinoGrande | 81.5% | — |

## Math

- phi-3-medium 14B: 25.2 (#249)
- Step 2 16k Exp 202412: 33.6 (#171)

| Benchmark | phi-3-medium 14B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Math | — | 1305 |
| MATH Level 5 | 17.6% | — |

## Knowledge

- phi-3-medium 14B: 9.1 (#301)
- Step 2 16k Exp 202412: 34.6 (#187)

| Benchmark | phi-3-medium 14B | Step 2 16k Exp 202412 |
|---|---|---|
| GPQA Diamond | 27.6% | — |
| LMArena Expert | — | 1279 |
| ARC (AI2) Challenge | 91.6% | — |
| MMLU | 78% | — |
| OpenBookQA | 87.4% | — |
| TriviaQA | 73.9% | — |

## Multilingual

- phi-3-medium 14B: —
- Step 2 16k Exp 202412: 43.9 (#176)

| Benchmark | phi-3-medium 14B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Non-English | — | 1290 |
| LMArena Chinese | — | 1331 |
| LMArena Russian | — | 1324 |

## Instruction Following

- phi-3-medium 14B: —
- Step 2 16k Exp 202412: 68.1 (#187)

| Benchmark | phi-3-medium 14B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Instruction Following | — | 1287 |

## Long Context

- phi-3-medium 14B: —
- Step 2 16k Exp 202412: 39.7 (#165)

| Benchmark | phi-3-medium 14B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Longer Query | — | 1307 |

## Writing & Preference

- phi-3-medium 14B: —
- Step 2 16k Exp 202412: 52.5 (#168)

| Benchmark | phi-3-medium 14B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Text | — | 1321 |
| LMArena Creative Writing | — | 1328 |
| LMArena Multi-Turn | — | 1292 |

## FAQ

### Is phi-3-medium 14B better than Step 2 16k Exp 202412?

Step 2 16k Exp 202412 is the stronger model overall, scoring 38.6 to 29.1 on the Noometry Index.

### Is phi-3-medium 14B or Step 2 16k Exp 202412 better for coding?

Step 2 16k Exp 202412 scores higher on coding benchmarks: 37.9 versus 36.3 in the Noometry coding category.

### How many benchmarks do phi-3-medium 14B and Step 2 16k Exp 202412 share?

0 benchmarks have published results for both models. phi-3-medium 14B has 13 scored results on Noometry and Step 2 16k Exp 202412 has 12.