# DeepSeek V4.1 Flash vs Phi 3 Mini 128k Instruct

> DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 29.7 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-v4-1-flash-vs-phi-3-mini-128k-instruct
- Last updated: 2026-10-12
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. DeepSeek V4.1 Flash scores higher in 8 categories and Phi 3 Mini 128k Instruct in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek V4.1 Flash leads 65.4 to 27.1.

## Snapshot

| | DeepSeek V4.1 Flash | Phi 3 Mini 128k Instruct |
|---|---|---|
| Provider | DeepSeek | Microsoft |
| Noometry Index | 52.8 | 29.7 |
| Rank | 38 | 305 |
| Context | 1M | — |
| Input $/M | $0.15 | — |
| Output $/M | $0.60 | — |
| Weights | Open | Open |

## Coding

- DeepSeek V4.1 Flash: 52.9 (#32)
- Phi 3 Mini 128k Instruct: 28.8 (#312)

| Benchmark | DeepSeek V4.1 Flash | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Coding | 1506 | 1039 |
| LMArena WebDev | 1619 | — |
| SciCode | 51.9% | — |
| BigCodeBench Instruct | — | 29.6% |
| BigCodeBench Complete | — | 40.6% |
| ALE-Bench | 1,092 | — |

## Agentic & Tool Use

- DeepSeek V4.1 Flash: 31.2 (#69)
- Phi 3 Mini 128k Instruct: —

| Benchmark | DeepSeek V4.1 Flash | Phi 3 Mini 128k Instruct |
|---|---|---|
| APEX-Agents | 39.5% | — |
| GDP.pdf | 19.8% | — |

## Reasoning

- DeepSeek V4.1 Flash: 50.2 (#36)
- Phi 3 Mini 128k Instruct: 19.6 (#256)

| Benchmark | DeepSeek V4.1 Flash | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1483 | 1028 |
| NYT Connections (extended) | 89.6% | — |
| CritPt | 14.3% | — |
| Mystery Game Puzzles | 43% | — |
| DTBench | 89.9% | — |
| LMCA | 47% | — |
| Surface Evolver Bench | 46.3% | — |
| Epoch Capabilities Index | 154.9 | — |

## Math

- DeepSeek V4.1 Flash: 66.7 (#25)
- Phi 3 Mini 128k Instruct: 31.6 (#222)

| Benchmark | DeepSeek V4.1 Flash | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Math | 1477 | 1089 |
| FrontierMath (Tiers 1-3) | 67.4% | — |
| FrontierMath Tier 4 | 26.8% | — |
| OTIS Mock AIME 2024-2025 | 98.3% | — |
| ProofBench | 54% | — |

## Knowledge

- DeepSeek V4.1 Flash: 57.9 (#38)
- Phi 3 Mini 128k Instruct: 26.8 (#254)

| Benchmark | DeepSeek V4.1 Flash | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Expert | 1506 | 984 |
| GPQA Diamond | 89.8% | — |

## Multimodal

- DeepSeek V4.1 Flash: 39.1 (#61)
- Phi 3 Mini 128k Instruct: —

| Benchmark | DeepSeek V4.1 Flash | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Vision | 1277 | — |
| Furniture Assembly | 34.2% | — |

## Multilingual

- DeepSeek V4.1 Flash: 55.0 (#35)
- Phi 3 Mini 128k Instruct: 25.2 (#285)

| Benchmark | DeepSeek V4.1 Flash | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Non-English | 1448 | 1000 |
| LMArena Chinese | 1497 | 1016 |
| LMArena French | 1452 | 1039 |
| LMArena German | 1484 | 1006 |
| LMArena Japanese | 1412 | 899 |
| LMArena Korean | 1452 | 856 |
| LMArena Russian | 1471 | 1004 |
| LMArena Spanish | 1459 | 1059 |

## Instruction Following

- DeepSeek V4.1 Flash: 77.3 (#26)
- Phi 3 Mini 128k Instruct: 51.8 (#294)

| Benchmark | DeepSeek V4.1 Flash | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Instruction Following | 1474 | 1023 |

## Long Context

- DeepSeek V4.1 Flash: 45.2 (#47)
- Phi 3 Mini 128k Instruct: 30.4 (#289)

| Benchmark | DeepSeek V4.1 Flash | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Longer Query | 1475 | 996 |

## Writing & Preference

- DeepSeek V4.1 Flash: 65.4 (#48)
- Phi 3 Mini 128k Instruct: 27.1 (#301)

| Benchmark | DeepSeek V4.1 Flash | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Text | 1462 | 1050 |
| LMArena Creative Writing | 1435 | 1024 |
| LMArena Multi-Turn | 1457 | 989 |
| EQ-Bench Creative Writing | 1540 | — |

## FAQ

### Is DeepSeek V4.1 Flash better than Phi 3 Mini 128k Instruct?

DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 29.7 on the Noometry Index.

### Is DeepSeek V4.1 Flash or Phi 3 Mini 128k Instruct better for coding?

DeepSeek V4.1 Flash scores higher on coding benchmarks: 52.9 versus 28.8 in the Noometry coding category.

### How many benchmarks do DeepSeek V4.1 Flash and Phi 3 Mini 128k Instruct share?

17 benchmarks have published results for both models. DeepSeek V4.1 Flash has 37 scored results on Noometry and Phi 3 Mini 128k Instruct has 19.