# Llama 3.1-8B vs Phi-2

> Llama 3.1-8B has enough public results to be ranked (#347); Phi-2 does not yet, so treat this comparison as directional.

- Canonical page: https://noometry.com/compare/llama-3-1-8b-vs-phi-2
- Last updated: 2026-10-10
- Shared benchmarks: 4

## Summary

- They share 4 benchmarks with published results for both.

## Snapshot

| | Llama 3.1-8B | Phi-2 |
|---|---|---|
| Provider | Meta | Microsoft |
| Noometry Index | 22.8 | — |
| Rank | 347 | — |
| Context | 128K | — |
| Input $/M | $0.05 | — |
| Output $/M | $0.08 | — |
| Weights | Open | Open |

## Coding

- Llama 3.1-8B: 19.9 (#335)
- Phi-2: —

| Benchmark | Llama 3.1-8B | Phi-2 |
|---|---|---|
| HumanEval+ | 62.8% | 45.1% |
| MBPP+ | 55.6% | 54.2% |
| SciCode | 13.2% | — |
| WeirdML | 1.7% | — |
| BigCodeBench Instruct | 32.8% | — |
| LMArena Coding | 1195 | — |
| BigCodeBench Complete | 40.5% | — |

## Agentic & Tool Use

- Llama 3.1-8B: 22.3 (#123)
- Phi-2: —

| Benchmark | Llama 3.1-8B | Phi-2 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25.8% | — |
| BALROG | 15.1% | — |

## Reasoning

- Llama 3.1-8B: 14.5 (#316)
- Phi-2: —

| Benchmark | Llama 3.1-8B | Phi-2 |
|---|---|---|
| Epoch Capabilities Index | 116.48 | 107.62 |
| CritPt | 0% | — |
| Chess Puzzles | 0% | — |
| LMArena Hard Prompts | 1175 | — |
| DTBench | 50.9% | — |
| LMCA | 5.4% | — |
| Adversarial NLI | — | 42.5% |
| BIG-Bench Hard | — | 59.4% |
| HellaSwag | — | 53.6% |
| PIQA | 81.2% | — |
| WinoGrande | — | 54.7% |

## Math

- Llama 3.1-8B: 9.5 (#311)
- Phi-2: —

| Benchmark | Llama 3.1-8B | Phi-2 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.7% | — |
| Omni-MATH | 13.7% | — |
| LMArena Math | 1179 | — |
| MATH Level 5 | 22.9% | — |
| GSM8K | 82.4% | — |

## Knowledge

- Llama 3.1-8B: 8.0 (#302)
- Phi-2: —

| Benchmark | Llama 3.1-8B | Phi-2 |
|---|---|---|
| MMLU | 56.1% | 58.4% |
| GPQA Diamond | 27% | — |
| MMLU-Pro | 40.6% | — |
| GPQA (HELM) | 24.7% | — |
| LMArena Expert | 1144 | — |
| ARC (AI2) Challenge | — | 75.9% |
| BoolQ | 82.8% | — |
| OpenBookQA | — | 73.6% |
| TriviaQA | — | 45.2% |

## Multilingual

- Llama 3.1-8B: 34.2 (#244)
- Phi-2: —

| Benchmark | Llama 3.1-8B | Phi-2 |
|---|---|---|
| LMArena Non-English | 1148 | — |
| LMArena Chinese | 1151 | — |
| LMArena French | 1176 | — |
| LMArena German | 1144 | — |
| LMArena Japanese | 1061 | — |
| LMArena Korean | 1053 | — |
| LMArena Russian | 1158 | — |
| LMArena Spanish | 1169 | — |

## Instruction Following

- Llama 3.1-8B: 59.1 (#253)
- Phi-2: —

| Benchmark | Llama 3.1-8B | Phi-2 |
|---|---|---|
| IFEval | 74.3% | — |
| LMArena Instruction Following | 1159 | — |

## Long Context

- Llama 3.1-8B: 35.8 (#233)
- Phi-2: —

| Benchmark | Llama 3.1-8B | Phi-2 |
|---|---|---|
| LMArena Longer Query | 1182 | — |

## Writing & Preference

- Llama 3.1-8B: 29.9 (#285)
- Phi-2: —

| Benchmark | Llama 3.1-8B | Phi-2 |
|---|---|---|
| LMArena Text | 1187 | — |
| LMArena Creative Writing | 1154 | — |
| EQ-Bench Creative Writing | 713 | — |
| WildBench | 68.7% | — |
| LMArena Multi-Turn | 1172 | — |

## FAQ

### Is Llama 3.1-8B better than Phi-2?

Llama 3.1-8B has enough public results to be ranked (#347); Phi-2 does not yet, so treat this comparison as directional.

### How many benchmarks do Llama 3.1-8B and Phi-2 share?

4 benchmarks have published results for both models. Llama 3.1-8B has 43 scored results on Noometry and Phi-2 has 11.