# Llama 13b vs Phi-1.5

> Llama 13b has enough public results to be ranked (#344); Phi-1.5 does not yet, so treat this comparison as directional.

- Canonical page: https://noometry.com/compare/llama-13b-vs-phi-1-5
- Last updated: 2026-10-10
- Shared benchmarks: 7

## Summary

- They share 7 benchmarks with published results for both.

## Snapshot

| | Llama 13b | Phi-1.5 |
|---|---|---|
| Provider | Meta | Microsoft |
| Noometry Index | 23.9 | — |
| Rank | 344 | — |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- Llama 13b: 20.9 (#332)
- Phi-1.5: —

| Benchmark | Llama 13b | Phi-1.5 |
|---|---|---|
| LMArena Coding | 683 | — |

## Reasoning

- Llama 13b: 13.4 (#327)
- Phi-1.5: —

| Benchmark | Llama 13b | Phi-1.5 |
|---|---|---|
| Epoch Capabilities Index | 100.09 | 90.82 |
| HellaSwag | 79.2% | 47.6% |
| WinoGrande | 73% | 73.4% |
| LMArena Hard Prompts | 728 | — |
| BIG-Bench Hard | 37.9% | — |
| LAMBADA | 75.2% | — |
| PIQA | 80.1% | — |

## Math

- Llama 13b: 24.4 (#259)
- Phi-1.5: —

| Benchmark | Llama 13b | Phi-1.5 |
|---|---|---|
| LMArena Math | 838 | — |
| GSM8K | 20.6% | — |

## Knowledge

- Llama 13b: —
- Phi-1.5: —

| Benchmark | Llama 13b | Phi-1.5 |
|---|---|---|
| ARC (AI2) Challenge | 52.7% | 44.4% |
| BoolQ | 78.7% | 75.8% |
| MMLU | 47.7% | 37.6% |
| OpenBookQA | 56.4% | 37.2% |
| TriviaQA | 77.9% | — |

## Multimodal

- Llama 13b: —
- Phi-1.5: —

| Benchmark | Llama 13b | Phi-1.5 |
|---|---|---|
| ScienceQA | 43.3% | — |

## Multilingual

- Llama 13b: 16.8 (#292)
- Phi-1.5: —

| Benchmark | Llama 13b | Phi-1.5 |
|---|---|---|
| LMArena Non-English | 819 | — |

## Instruction Following

- Llama 13b: 36.9 (#300)
- Phi-1.5: —

| Benchmark | Llama 13b | Phi-1.5 |
|---|---|---|
| LMArena Instruction Following | 781 | — |

## Writing & Preference

- Llama 13b: 13.9 (#307)
- Phi-1.5: —

| Benchmark | Llama 13b | Phi-1.5 |
|---|---|---|
| LMArena Text | 834 | — |
| LMArena Creative Writing | 794 | — |
| LMArena Multi-Turn | 753 | — |

## FAQ

### Is Llama 13b better than Phi-1.5?

Llama 13b has enough public results to be ranked (#344); Phi-1.5 does not yet, so treat this comparison as directional.

### How many benchmarks do Llama 13b and Phi-1.5 share?

7 benchmarks have published results for both models. Llama 13b has 21 scored results on Noometry and Phi-1.5 has 7.