# Llama2 70b Steerlm Chat vs phi-3-medium 14B

> Llama2 70b Steerlm Chat is the stronger model overall, scoring 31.2 to 29.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/llama2-70b-steerlm-chat-vs-phi-3-medium-14b
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in coding, where phi-3-medium 14B leads 36.3 to 29.3.

## Snapshot

| | Llama2 70b Steerlm Chat | phi-3-medium 14B |
|---|---|---|
| Provider | NVIDIA | Microsoft |
| Noometry Index | 31.2 | 29.1 |
| Rank | 265 | 306 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- Llama2 70b Steerlm Chat: 29.3 (#295)
- phi-3-medium 14B: 36.3 (#198)

| Benchmark | Llama2 70b Steerlm Chat | phi-3-medium 14B |
|---|---|---|
| BigCodeBench Instruct | — | 37.6% |
| LMArena Coding | 1025 | — |
| BigCodeBench Complete | — | 48.7% |

## Reasoning

- Llama2 70b Steerlm Chat: 19.1 (#245)
- phi-3-medium 14B: —

| Benchmark | Llama2 70b Steerlm Chat | phi-3-medium 14B |
|---|---|---|
| LMArena Hard Prompts | 1047 | — |
| Adversarial NLI | — | 55.8% |
| BIG-Bench Hard | — | 81.4% |
| Epoch Capabilities Index | — | 121.18 |
| HellaSwag | — | 82.4% |
| WinoGrande | — | 81.5% |

## Math

- Llama2 70b Steerlm Chat: 28.8 (#223)
- phi-3-medium 14B: 25.2 (#249)

| Benchmark | Llama2 70b Steerlm Chat | phi-3-medium 14B |
|---|---|---|
| LMArena Math | 1072 | — |
| MATH Level 5 | — | 17.6% |

## Knowledge

- Llama2 70b Steerlm Chat: —
- phi-3-medium 14B: 9.1 (#301)

| Benchmark | Llama2 70b Steerlm Chat | phi-3-medium 14B |
|---|---|---|
| GPQA Diamond | — | 27.6% |
| ARC (AI2) Challenge | — | 91.6% |
| MMLU | — | 78% |
| OpenBookQA | — | 87.4% |
| TriviaQA | — | 73.9% |

## Multilingual

- Llama2 70b Steerlm Chat: 28.9 (#265)
- phi-3-medium 14B: —

| Benchmark | Llama2 70b Steerlm Chat | phi-3-medium 14B |
|---|---|---|
| LMArena Non-English | 1064 | — |

## Instruction Following

- Llama2 70b Steerlm Chat: 54.5 (#274)
- phi-3-medium 14B: —

| Benchmark | Llama2 70b Steerlm Chat | phi-3-medium 14B |
|---|---|---|
| LMArena Instruction Following | 1061 | — |

## Long Context

- Llama2 70b Steerlm Chat: 30.4 (#283)
- phi-3-medium 14B: —

| Benchmark | Llama2 70b Steerlm Chat | phi-3-medium 14B |
|---|---|---|
| LMArena Longer Query | 998 | — |

## Writing & Preference

- Llama2 70b Steerlm Chat: 31.8 (#278)
- phi-3-medium 14B: —

| Benchmark | Llama2 70b Steerlm Chat | phi-3-medium 14B |
|---|---|---|
| LMArena Text | 1098 | — |
| LMArena Creative Writing | 1091 | — |
| LMArena Multi-Turn | 1058 | — |

## FAQ

### Is Llama2 70b Steerlm Chat better than phi-3-medium 14B?

Llama2 70b Steerlm Chat is the stronger model overall, scoring 31.2 to 29.1 on the Noometry Index.

### Is Llama2 70b Steerlm Chat or phi-3-medium 14B better for coding?

phi-3-medium 14B scores higher on coding benchmarks: 36.3 versus 29.3 in the Noometry coding category.

### How many benchmarks do Llama2 70b Steerlm Chat and phi-3-medium 14B share?

0 benchmarks have published results for both models. Llama2 70b Steerlm Chat has 9 scored results on Noometry and phi-3-medium 14B has 13.