# DeepSeek LLM 67B vs Phi 3 Small 8k Instruct

> Phi 3 Small 8k Instruct is the stronger model overall, scoring 29.3 to 24.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/deepseek-llm-67b-vs-phi-3-small-8k-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 10

## Summary

- They share 10 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 6 categories and Phi 3 Small 8k Instruct in 2 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Phi 3 Small 8k Instruct leads 29.1 to 7.0.

## Snapshot

| | DeepSeek LLM 67B | Phi 3 Small 8k Instruct |
|---|---|---|
| Provider | DeepSeek | Microsoft |
| Noometry Index | 24.9 | 29.3 |
| Rank | 347 | 314 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- DeepSeek LLM 67B: 31.9 (#278)
- Phi 3 Small 8k Instruct: 27.9 (#318)

| Benchmark | DeepSeek LLM 67B | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Coding | 1096 | 1101 |
| LiveBench Coding | — | 20.3% |

## Reasoning

- DeepSeek LLM 67B: 16.5 (#304)
- Phi 3 Small 8k Instruct: 14.8 (#323)

| Benchmark | DeepSeek LLM 67B | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1070 | 1100 |
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | — | 15.9% |
| LiveBench Data Analysis | — | 30.3% |
| Adversarial NLI | — | 58.1% |
| BIG-Bench Hard | — | 79.1% |
| Epoch Capabilities Index | 110.5 | — |
| HellaSwag | — | 77% |
| LiveBench | — | 24% |
| WinoGrande | — | 81.5% |

## Math

- DeepSeek LLM 67B: 8.7 (#324)
- Phi 3 Small 8k Instruct: 27.6 (#248)

| Benchmark | DeepSeek LLM 67B | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Math | 1108 | 1151 |
| OTIS Mock AIME 2024-2025 | 0.8% | — |
| LiveBench Math | — | 17.6% |
| MATH Level 5 | 6.4% | — |

## Knowledge

- DeepSeek LLM 67B: 7.0 (#313)
- Phi 3 Small 8k Instruct: 29.1 (#240)

| Benchmark | DeepSeek LLM 67B | Phi 3 Small 8k Instruct |
|---|---|---|
| GPQA Diamond | 24.6% | — |
| LMArena Expert | — | 1067 |
| ARC (AI2) Challenge | — | 90.7% |
| MMLU | — | 75.7% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 58.1% |

## Multilingual

- DeepSeek LLM 67B: 29.4 (#267)
- Phi 3 Small 8k Instruct: 28.5 (#272)

| Benchmark | DeepSeek LLM 67B | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Non-English | 1073 | 1058 |
| LMArena Chinese | 1132 | 1061 |
| LMArena French | — | 1135 |
| LMArena German | — | 1080 |
| LMArena Japanese | — | 966 |
| LMArena Korean | — | 894 |
| LMArena Russian | — | 1111 |
| LMArena Spanish | — | 1111 |

## Instruction Following

- DeepSeek LLM 67B: 55.4 (#277)
- Phi 3 Small 8k Instruct: 51.9 (#292)

| Benchmark | DeepSeek LLM 67B | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Instruction Following | 1079 | 1087 |
| LiveBench Instruction Following | — | 47.2% |

## Long Context

- DeepSeek LLM 67B: 33.1 (#265)
- Phi 3 Small 8k Instruct: 33.0 (#267)

| Benchmark | DeepSeek LLM 67B | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Longer Query | 1092 | 1088 |

## Writing & Preference

- DeepSeek LLM 67B: 31.6 (#282)
- Phi 3 Small 8k Instruct: 31.1 (#284)

| Benchmark | DeepSeek LLM 67B | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Text | 1105 | 1110 |
| LMArena Creative Writing | 1067 | 1083 |
| LMArena Multi-Turn | 1082 | 1068 |
| LiveBench Language | — | 12.9% |

## FAQ

### Is DeepSeek LLM 67B better than Phi 3 Small 8k Instruct?

Phi 3 Small 8k Instruct is the stronger model overall, scoring 29.3 to 24.9 on the Noometry Index.

### Is DeepSeek LLM 67B or Phi 3 Small 8k Instruct better for coding?

DeepSeek LLM 67B scores higher on coding benchmarks: 31.9 versus 27.9 in the Noometry coding category.

### How many benchmarks do DeepSeek LLM 67B and Phi 3 Small 8k Instruct share?

10 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Phi 3 Small 8k Instruct has 32.