# DeepSeek-V3.1-Terminus vs Phi 3 Medium 4k Instruct

> DeepSeek-V3.1-Terminus is the stronger model overall, scoring 43.1 to 33.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-v3-1-terminus-vs-phi-3-medium-4k-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 10

## Summary

- They share 10 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 7 categories and Phi 3 Medium 4k Instruct in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-V3.1-Terminus leads 61.0 to 34.1.

## Snapshot

| | DeepSeek-V3.1-Terminus | Phi 3 Medium 4k Instruct |
|---|---|---|
| Provider | DeepSeek | Microsoft |
| Noometry Index | 43.1 | 33.0 |
| Rank | 97 | 250 |
| Context | 164K | — |
| Input $/M | $0.27 | — |
| Output $/M | $1 | — |
| Weights | Open | Open |

## Coding

- DeepSeek-V3.1-Terminus: 42.0 (#113)
- Phi 3 Medium 4k Instruct: 32.9 (#268)

| Benchmark | DeepSeek-V3.1-Terminus | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Coding | 1426 | 1130 |
| SciCode | 40.6% | — |
| ALE-Bench | 745.17 | — |

## Reasoning

- DeepSeek-V3.1-Terminus: 26.4 (#133)
- Phi 3 Medium 4k Instruct: 21.7 (#214)

| Benchmark | DeepSeek-V3.1-Terminus | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1426 | 1127 |
| Kagi LLM Benchmark | 57.4% | — |
| CritPt | 1.7% | — |
| DTBench | 81.3% | — |
| LMCA | 28.6% | — |

## Math

- DeepSeek-V3.1-Terminus: 38.5 (#137)
- Phi 3 Medium 4k Instruct: 33.4 (#202)

| Benchmark | DeepSeek-V3.1-Terminus | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Math | 1402 | 1173 |

## Knowledge

- DeepSeek-V3.1-Terminus: —
- Phi 3 Medium 4k Instruct: 30.2 (#229)

| Benchmark | DeepSeek-V3.1-Terminus | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Expert | — | 1108 |

## Multilingual

- DeepSeek-V3.1-Terminus: 52.1 (#92)
- Phi 3 Medium 4k Instruct: 30.6 (#263)

| Benchmark | DeepSeek-V3.1-Terminus | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Non-English | 1407 | 1094 |
| LMArena Russian | 1436 | 1145 |
| LMArena Chinese | — | 1108 |
| LMArena French | — | 1110 |
| LMArena German | — | 1101 |
| LMArena Japanese | — | 1042 |
| LMArena Korean | — | 954 |
| LMArena Spanish | — | 1095 |

## Instruction Following

- DeepSeek-V3.1-Terminus: 74.0 (#106)
- Phi 3 Medium 4k Instruct: 57.6 (#268)

| Benchmark | DeepSeek-V3.1-Terminus | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1404 | 1113 |

## Long Context

- DeepSeek-V3.1-Terminus: 43.4 (#97)
- Phi 3 Medium 4k Instruct: 34.0 (#255)

| Benchmark | DeepSeek-V3.1-Terminus | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1421 | 1120 |

## Writing & Preference

- DeepSeek-V3.1-Terminus: 61.0 (#92)
- Phi 3 Medium 4k Instruct: 34.1 (#272)

| Benchmark | DeepSeek-V3.1-Terminus | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Text | 1419 | 1138 |
| LMArena Creative Writing | 1403 | 1107 |
| LMArena Multi-Turn | 1411 | 1088 |

## FAQ

### Is DeepSeek-V3.1-Terminus better than Phi 3 Medium 4k Instruct?

DeepSeek-V3.1-Terminus is the stronger model overall, scoring 43.1 to 33.0 on the Noometry Index.

### Is DeepSeek-V3.1-Terminus or Phi 3 Medium 4k Instruct better for coding?

DeepSeek-V3.1-Terminus scores higher on coding benchmarks: 42.0 versus 32.9 in the Noometry coding category.

### How many benchmarks do DeepSeek-V3.1-Terminus and Phi 3 Medium 4k Instruct share?

10 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and Phi 3 Medium 4k Instruct has 17.