# DeepSeek-V2.5 (Sep 2024) vs Phi 3 Medium 4k Instruct

> DeepSeek-V2.5 (Sep 2024) is the stronger model overall, scoring 37.6 to 33.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-v2-5-vs-phi-3-medium-4k-instruct
- Last updated: 2026-10-12
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 7 categories and Phi 3 Medium 4k Instruct in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-V2.5 (Sep 2024) leads 49.8 to 34.1.

## Snapshot

| | DeepSeek-V2.5 (Sep 2024) | Phi 3 Medium 4k Instruct |
|---|---|---|
| Provider | DeepSeek | Microsoft |
| Noometry Index | 37.6 | 33.0 |
| Rank | 200 | 250 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- DeepSeek-V2.5 (Sep 2024): 31.7 (#281)
- Phi 3 Medium 4k Instruct: 32.9 (#268)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Coding | 1309 | 1130 |
| Aider Polyglot | 17.8% | — |
| BigCodeBench Instruct | 48.6% | — |
| BigCodeBench Complete | 53.2% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |

## Reasoning

- DeepSeek-V2.5 (Sep 2024): 25.6 (#145)
- Phi 3 Medium 4k Instruct: 21.7 (#214)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1127 |

## Math

- DeepSeek-V2.5 (Sep 2024): 35.9 (#177)
- Phi 3 Medium 4k Instruct: 33.4 (#202)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Math | 1288 | 1173 |

## Knowledge

- DeepSeek-V2.5 (Sep 2024): 34.8 (#193)
- Phi 3 Medium 4k Instruct: 30.2 (#229)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Expert | 1266 | 1108 |

## Multilingual

- DeepSeek-V2.5 (Sep 2024): 42.5 (#193)
- Phi 3 Medium 4k Instruct: 30.6 (#263)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Non-English | 1273 | 1094 |
| LMArena Chinese | 1318 | 1108 |
| LMArena French | 1289 | 1110 |
| LMArena German | 1258 | 1101 |
| LMArena Japanese | 1228 | 1042 |
| LMArena Korean | 1209 | 954 |
| LMArena Russian | 1289 | 1145 |
| LMArena Spanish | 1248 | 1095 |

## Instruction Following

- DeepSeek-V2.5 (Sep 2024): 67.5 (#194)
- Phi 3 Medium 4k Instruct: 57.6 (#268)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1280 | 1113 |

## Long Context

- DeepSeek-V2.5 (Sep 2024): 39.5 (#174)
- Phi 3 Medium 4k Instruct: 34.0 (#255)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1301 | 1120 |

## Writing & Preference

- DeepSeek-V2.5 (Sep 2024): 49.8 (#187)
- Phi 3 Medium 4k Instruct: 34.1 (#272)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Text | 1294 | 1138 |
| LMArena Creative Writing | 1285 | 1107 |
| LMArena Multi-Turn | 1297 | 1088 |

## FAQ

### Is DeepSeek-V2.5 (Sep 2024) better than Phi 3 Medium 4k Instruct?

DeepSeek-V2.5 (Sep 2024) is the stronger model overall, scoring 37.6 to 33.0 on the Noometry Index.

### Is DeepSeek-V2.5 (Sep 2024) or Phi 3 Medium 4k Instruct better for coding?

Phi 3 Medium 4k Instruct scores higher on coding benchmarks: 32.9 versus 31.7 in the Noometry coding category.

### How many benchmarks do DeepSeek-V2.5 (Sep 2024) and Phi 3 Medium 4k Instruct share?

17 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and Phi 3 Medium 4k Instruct has 17.