# Llama 3.1-70B vs Phi-3.5-mini

> Llama 3.1-70B has enough public results to be ranked (#299); Phi-3.5-mini does not yet, so treat this comparison as directional.

- Canonical page: https://noometry.com/compare/llama-3-1-70b-vs-phi-3-5-mini
- Last updated: 2026-10-10
- Shared benchmarks: 2

## Summary

- They share 2 benchmarks with published results for both. Llama 3.1-70B scores higher in 0 categories and Phi-3.5-mini in 1 category; one gap is clear of the uncertainty.
- The widest gap is in coding, where Phi-3.5-mini leads 34.0 to 29.8.
- The biggest single-benchmark swing is BigCodeBench Complete: 54.8% for Llama 3.1-70B and 38.5% for Phi-3.5-mini.

## Snapshot

| | Llama 3.1-70B | Phi-3.5-mini |
|---|---|---|
| Provider | Meta | Microsoft |
| Noometry Index | 29.4 | 36.4 |
| Rank | 299 | — |
| Context | 128K | — |
| Input $/M | $0.40 | — |
| Output $/M | $0.40 | — |
| Weights | Open | Open |

## Coding

- Llama 3.1-70B: 29.8 (#292)
- Phi-3.5-mini: 34.0 (#231)

| Benchmark | Llama 3.1-70B | Phi-3.5-mini |
|---|---|---|
| BigCodeBench Instruct | 46.1% | 32.8% |
| BigCodeBench Complete | 54.8% | 38.5% |
| WeirdML | 9% | — |
| LMArena Coding | 1260 | — |

## Agentic & Tool Use

- Llama 3.1-70B: 24.9 (#104)
- Phi-3.5-mini: —

| Benchmark | Llama 3.1-70B | Phi-3.5-mini |
|---|---|---|
| TheAgentCompany | 6.9% | — |
| BALROG | 27.9% | — |

## Reasoning

- Llama 3.1-70B: 20.8 (#215)
- Phi-3.5-mini: —

| Benchmark | Llama 3.1-70B | Phi-3.5-mini |
|---|---|---|
| LMArena Hard Prompts | 1241 | — |
| DTBench | 60% | — |
| LMCA | 14.8% | — |
| Epoch Capabilities Index | 125.91 | — |
| PIQA | — | 81% |

## Math

- Llama 3.1-70B: 12.7 (#298)
- Phi-3.5-mini: —

| Benchmark | Llama 3.1-70B | Phi-3.5-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 3.6% | — |
| Omni-MATH | 21% | — |
| LMArena Math | 1252 | — |
| MATH Level 5 | 36.7% | — |
| GSM8K | — | 86.2% |

## Knowledge

- Llama 3.1-70B: 24.1 (#264)
- Phi-3.5-mini: —

| Benchmark | Llama 3.1-70B | Phi-3.5-mini |
|---|---|---|
| GPQA Diamond | 44.2% | — |
| MMLU-Pro | 65.3% | — |
| GPQA (HELM) | 42.6% | — |
| LMArena Expert | 1209 | — |
| BoolQ | — | 78% |
| MMLU | 80.1% | — |

## Multilingual

- Llama 3.1-70B: 38.9 (#220)
- Phi-3.5-mini: —

| Benchmark | Llama 3.1-70B | Phi-3.5-mini |
|---|---|---|
| LMArena Non-English | 1219 | — |
| LMArena Chinese | 1215 | — |
| LMArena French | 1260 | — |
| LMArena German | 1222 | — |
| LMArena Japanese | 1132 | — |
| LMArena Korean | 1140 | — |
| LMArena Russian | 1234 | — |
| LMArena Spanish | 1253 | — |

## Instruction Following

- Llama 3.1-70B: 65.5 (#218)
- Phi-3.5-mini: —

| Benchmark | Llama 3.1-70B | Phi-3.5-mini |
|---|---|---|
| IFEval | 82.1% | — |
| LMArena Instruction Following | 1231 | — |

## Long Context

- Llama 3.1-70B: 37.6 (#208)
- Phi-3.5-mini: —

| Benchmark | Llama 3.1-70B | Phi-3.5-mini |
|---|---|---|
| LMArena Longer Query | 1241 | — |

## Writing & Preference

- Llama 3.1-70B: 35.6 (#262)
- Phi-3.5-mini: —

| Benchmark | Llama 3.1-70B | Phi-3.5-mini |
|---|---|---|
| LMArena Text | 1261 | — |
| LMArena Creative Writing | 1232 | — |
| EQ-Bench Creative Writing | 784 | — |
| WildBench | 75.8% | — |
| LMArena Multi-Turn | 1256 | — |

## FAQ

### Is Llama 3.1-70B better than Phi-3.5-mini?

Llama 3.1-70B has enough public results to be ranked (#299); Phi-3.5-mini does not yet, so treat this comparison as directional.

### Is Llama 3.1-70B or Phi-3.5-mini better for coding?

Phi-3.5-mini scores higher on coding benchmarks: 34.0 versus 29.8 in the Noometry coding category.

### How many benchmarks do Llama 3.1-70B and Phi-3.5-mini share?

2 benchmarks have published results for both models. Llama 3.1-70B has 35 scored results on Noometry and Phi-3.5-mini has 5.