# Llama 3-70B vs Phi 3 Small 8k Instruct

> Llama 3-70B and Phi 3 Small 8k Instruct score almost the same on the Noometry Index (28.8 vs 29.3), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/llama-3-70b-vs-phi-3-small-8k-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. Llama 3-70B scores higher in 6 categories and Phi 3 Small 8k Instruct in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Phi 3 Small 8k Instruct leads 27.6 to 12.8.

## Snapshot

| | Llama 3-70B | Phi 3 Small 8k Instruct |
|---|---|---|
| Provider | Meta | Microsoft |
| Noometry Index | 28.8 | 29.3 |
| Rank | 323 | 314 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- Llama 3-70B: 35.8 (#218)
- Phi 3 Small 8k Instruct: 27.9 (#318)

| Benchmark | Llama 3-70B | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Coding | 1206 | 1101 |
| BigCodeBench Instruct | 43.6% | — |
| LiveBench Coding | — | 20.3% |
| BigCodeBench Complete | 54.5% | — |
| HumanEval+ | 72% | — |
| MBPP+ | 69% | — |

## Agentic & Tool Use

- Llama 3-70B: 21.1 (#139)
- Phi 3 Small 8k Instruct: —

| Benchmark | Llama 3-70B | Phi 3 Small 8k Instruct |
|---|---|---|
| Cybench | 5% | — |

## Reasoning

- Llama 3-70B: 18.0 (#288)
- Phi 3 Small 8k Instruct: 14.8 (#323)

| Benchmark | Llama 3-70B | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1195 | 1100 |
| WinoGrande | 83.5% | 81.5% |
| Kagi LLM Benchmark | 35.1% | — |
| LiveBench Reasoning | — | 15.9% |
| DTBench | 54.2% | — |
| LiveBench Data Analysis | — | 30.3% |
| Adversarial NLI | — | 58.1% |
| BIG-Bench Hard | — | 79.1% |
| Epoch Capabilities Index | 122.93 | — |
| ForecastBench | 57.1 | — |
| HellaSwag | — | 77% |
| LiveBench | — | 24% |

## Math

- Llama 3-70B: 12.8 (#305)
- Phi 3 Small 8k Instruct: 27.6 (#248)

| Benchmark | Llama 3-70B | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Math | 1218 | 1151 |
| OTIS Mock AIME 2024-2025 | 4.3% | — |
| LiveBench Math | — | 17.6% |
| MATH Level 5 | 22.6% | — |

## Knowledge

- Llama 3-70B: 20.8 (#277)
- Phi 3 Small 8k Instruct: 29.1 (#240)

| Benchmark | Llama 3-70B | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Expert | 1149 | 1067 |
| MMLU | 79.3% | 75.7% |
| GPQA Diamond | 40.6% | — |
| ARC (AI2) Challenge | — | 90.7% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 58.1% |

## Multilingual

- Llama 3-70B: 33.6 (#251)
- Phi 3 Small 8k Instruct: 28.5 (#272)

| Benchmark | Llama 3-70B | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Non-English | 1142 | 1058 |
| LMArena Chinese | 1114 | 1061 |
| LMArena French | 1232 | 1135 |
| LMArena German | 1169 | 1080 |
| LMArena Japanese | 1017 | 966 |
| LMArena Korean | 1017 | 894 |
| LMArena Russian | 1159 | 1111 |
| LMArena Spanish | 1241 | 1111 |

## Instruction Following

- Llama 3-70B: 62.5 (#238)
- Phi 3 Small 8k Instruct: 51.9 (#292)

| Benchmark | Llama 3-70B | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Instruction Following | 1194 | 1087 |
| LiveBench Instruction Following | — | 47.2% |

## Long Context

- Llama 3-70B: 35.6 (#240)
- Phi 3 Small 8k Instruct: 33.0 (#267)

| Benchmark | Llama 3-70B | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Longer Query | 1174 | 1088 |

## Writing & Preference

- Llama 3-70B: 42.8 (#231)
- Phi 3 Small 8k Instruct: 31.1 (#284)

| Benchmark | Llama 3-70B | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Text | 1221 | 1110 |
| LMArena Creative Writing | 1210 | 1083 |
| LMArena Multi-Turn | 1223 | 1068 |
| LiveBench Language | — | 12.9% |

## FAQ

### Is Llama 3-70B better than Phi 3 Small 8k Instruct?

Llama 3-70B and Phi 3 Small 8k Instruct score almost the same on the Noometry Index (28.8 vs 29.3), so choose on price, context window or the category you care about most.

### Is Llama 3-70B or Phi 3 Small 8k Instruct better for coding?

Llama 3-70B scores higher on coding benchmarks: 35.8 versus 27.9 in the Noometry coding category.

### How many benchmarks do Llama 3-70B and Phi 3 Small 8k Instruct share?

19 benchmarks have published results for both models. Llama 3-70B has 31 scored results on Noometry and Phi 3 Small 8k Instruct has 32.