# DeepSeek LLM 67B vs Phi-3.5-mini

> DeepSeek LLM 67B has enough public results to be ranked (#347); Phi-3.5-mini does not yet, so treat this comparison as directional.

- Canonical page: https://noometry.com/compare/deepseek-llm-67b-vs-phi-3-5-mini
- Last updated: 2026-10-12
- Shared benchmarks: 0

## Snapshot

| | DeepSeek LLM 67B | Phi-3.5-mini |
|---|---|---|
| Provider | DeepSeek | Microsoft |
| Noometry Index | 24.9 | 36.9 |
| Rank | 347 | — |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- DeepSeek LLM 67B: 31.9 (#278)
- Phi-3.5-mini: 34.6 (#232)

| Benchmark | DeepSeek LLM 67B | Phi-3.5-mini |
|---|---|---|
| BigCodeBench Instruct | — | 32.8% |
| LMArena Coding | 1096 | — |
| BigCodeBench Complete | — | 38.5% |

## Reasoning

- DeepSeek LLM 67B: 16.5 (#304)
- Phi-3.5-mini: —

| Benchmark | DeepSeek LLM 67B | Phi-3.5-mini |
|---|---|---|
| Chess Puzzles | 0% | — |
| LMArena Hard Prompts | 1070 | — |
| Epoch Capabilities Index | 110.5 | — |
| PIQA | — | 81% |

## Math

- DeepSeek LLM 67B: 8.7 (#324)
- Phi-3.5-mini: —

| Benchmark | DeepSeek LLM 67B | Phi-3.5-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.8% | — |
| LMArena Math | 1108 | — |
| MATH Level 5 | 6.4% | — |
| GSM8K | — | 86.2% |

## Knowledge

- DeepSeek LLM 67B: 7.0 (#313)
- Phi-3.5-mini: —

| Benchmark | DeepSeek LLM 67B | Phi-3.5-mini |
|---|---|---|
| GPQA Diamond | 24.6% | — |
| BoolQ | — | 78% |

## Multilingual

- DeepSeek LLM 67B: 29.4 (#267)
- Phi-3.5-mini: —

| Benchmark | DeepSeek LLM 67B | Phi-3.5-mini |
|---|---|---|
| LMArena Non-English | 1073 | — |
| LMArena Chinese | 1132 | — |

## Instruction Following

- DeepSeek LLM 67B: 55.4 (#277)
- Phi-3.5-mini: —

| Benchmark | DeepSeek LLM 67B | Phi-3.5-mini |
|---|---|---|
| LMArena Instruction Following | 1079 | — |

## Long Context

- DeepSeek LLM 67B: 33.1 (#265)
- Phi-3.5-mini: —

| Benchmark | DeepSeek LLM 67B | Phi-3.5-mini |
|---|---|---|
| LMArena Longer Query | 1092 | — |

## Writing & Preference

- DeepSeek LLM 67B: 31.6 (#282)
- Phi-3.5-mini: —

| Benchmark | DeepSeek LLM 67B | Phi-3.5-mini |
|---|---|---|
| LMArena Text | 1105 | — |
| LMArena Creative Writing | 1067 | — |
| LMArena Multi-Turn | 1082 | — |

## FAQ

### Is DeepSeek LLM 67B better than Phi-3.5-mini?

DeepSeek LLM 67B has enough public results to be ranked (#347); Phi-3.5-mini does not yet, so treat this comparison as directional.

### Is DeepSeek LLM 67B or Phi-3.5-mini better for coding?

Phi-3.5-mini scores higher on coding benchmarks: 34.6 versus 31.9 in the Noometry coding category.

### How many benchmarks do DeepSeek LLM 67B and Phi-3.5-mini share?

0 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Phi-3.5-mini has 5.