# Granite 3.1 8b Instruct vs Llama 13b

> Granite 3.1 8b Instruct is the stronger model overall, scoring 31.8 to 23.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/granite-3-1-8b-instruct-vs-llama-13b
- Last updated: 2026-10-10
- Shared benchmarks: 8

## Summary

- They share 8 benchmarks with published results for both. Granite 3.1 8b Instruct scores higher in 6 categories and Llama 13b in 0 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Granite 3.1 8b Instruct leads 58.9 to 36.9.

## Snapshot

| | Granite 3.1 8b Instruct | Llama 13b |
|---|---|---|
| Provider | IBM | Meta |
| Noometry Index | 31.8 | 23.9 |
| Rank | 256 | 344 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- Granite 3.1 8b Instruct: 33.9 (#232)
- Llama 13b: 20.9 (#332)

| Benchmark | Granite 3.1 8b Instruct | Llama 13b |
|---|---|---|
| LMArena Coding | 1186 | 683 |

## Agentic & Tool Use

- Granite 3.1 8b Instruct: 23.9 (#113)
- Llama 13b: —

| Benchmark | Granite 3.1 8b Instruct | Llama 13b |
|---|---|---|
| Berkeley Function Calling Leaderboard | 27.1% | — |

## Reasoning

- Granite 3.1 8b Instruct: 21.2 (#204)
- Llama 13b: 13.4 (#327)

| Benchmark | Granite 3.1 8b Instruct | Llama 13b |
|---|---|---|
| LMArena Hard Prompts | 1146 | 728 |
| BIG-Bench Hard | — | 37.9% |
| Epoch Capabilities Index | — | 100.09 |
| HellaSwag | — | 79.2% |
| LAMBADA | — | 75.2% |
| PIQA | — | 80.1% |
| WinoGrande | — | 73% |

## Math

- Granite 3.1 8b Instruct: 30.4 (#210)
- Llama 13b: 24.4 (#259)

| Benchmark | Granite 3.1 8b Instruct | Llama 13b |
|---|---|---|
| LMArena Math | 1152 | 838 |
| GSM8K | — | 20.6% |

## Knowledge

- Granite 3.1 8b Instruct: 30.6 (#218)
- Llama 13b: —

| Benchmark | Granite 3.1 8b Instruct | Llama 13b |
|---|---|---|
| LMArena Expert | 1142 | — |
| ARC (AI2) Challenge | — | 52.7% |
| BoolQ | — | 78.7% |
| MMLU | — | 47.7% |
| OpenBookQA | — | 56.4% |
| TriviaQA | — | 77.9% |

## Multimodal

- Granite 3.1 8b Instruct: —
- Llama 13b: —

| Benchmark | Granite 3.1 8b Instruct | Llama 13b |
|---|---|---|
| ScienceQA | — | 43.3% |

## Multilingual

- Granite 3.1 8b Instruct: 31.1 (#255)
- Llama 13b: 16.8 (#292)

| Benchmark | Granite 3.1 8b Instruct | Llama 13b |
|---|---|---|
| LMArena Non-English | 1099 | 819 |
| LMArena Chinese | 1145 | — |
| LMArena Russian | 1092 | — |

## Instruction Following

- Granite 3.1 8b Instruct: 58.9 (#254)
- Llama 13b: 36.9 (#300)

| Benchmark | Granite 3.1 8b Instruct | Llama 13b |
|---|---|---|
| LMArena Instruction Following | 1131 | 781 |

## Long Context

- Granite 3.1 8b Instruct: 35.2 (#236)
- Llama 13b: —

| Benchmark | Granite 3.1 8b Instruct | Llama 13b |
|---|---|---|
| LMArena Longer Query | 1162 | — |

## Writing & Preference

- Granite 3.1 8b Instruct: 35.7 (#261)
- Llama 13b: 13.9 (#307)

| Benchmark | Granite 3.1 8b Instruct | Llama 13b |
|---|---|---|
| LMArena Text | 1150 | 834 |
| LMArena Creative Writing | 1129 | 794 |
| LMArena Multi-Turn | 1108 | 753 |

## FAQ

### Is Granite 3.1 8b Instruct better than Llama 13b?

Granite 3.1 8b Instruct is the stronger model overall, scoring 31.8 to 23.9 on the Noometry Index.

### Is Granite 3.1 8b Instruct or Llama 13b better for coding?

Granite 3.1 8b Instruct scores higher on coding benchmarks: 33.9 versus 20.9 in the Noometry coding category.

### How many benchmarks do Granite 3.1 8b Instruct and Llama 13b share?

8 benchmarks have published results for both models. Granite 3.1 8b Instruct has 13 scored results on Noometry and Llama 13b has 21.