# Granite 3.1 8b Instruct vs StarCoder 2 3B

> Granite 3.1 8b Instruct has enough public results to be ranked (#258); StarCoder 2 3B does not yet, so treat this comparison as directional.

- Canonical page: https://noometry.com/compare/granite-3-1-8b-instruct-vs-starcoder-2-3b
- Last updated: 2026-10-11
- Shared benchmarks: 0

## Snapshot

| | Granite 3.1 8b Instruct | StarCoder 2 3B |
|---|---|---|
| Provider | IBM | NVIDIA |
| Noometry Index | 32.4 | 36.3 |
| Rank | 258 | — |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- Granite 3.1 8b Instruct: 34.5 (#233)
- StarCoder 2 3B: 33.5

| Benchmark | Granite 3.1 8b Instruct | StarCoder 2 3B |
|---|---|---|
| LMArena Coding | 1186 | — |
| BigCodeBench Complete | — | 21.4% |
| HumanEval+ | — | 27.4% |

## Agentic & Tool Use

- Granite 3.1 8b Instruct: 24.1 (#120)
- StarCoder 2 3B: —

| Benchmark | Granite 3.1 8b Instruct | StarCoder 2 3B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 27.1% | — |

## Reasoning

- Granite 3.1 8b Instruct: 22.1 (#207)
- StarCoder 2 3B: —

| Benchmark | Granite 3.1 8b Instruct | StarCoder 2 3B |
|---|---|---|
| LMArena Hard Prompts | 1145 | — |
| Epoch Capabilities Index | — | 88.76 |
| WinoGrande | — | 57.1% |

## Math

- Granite 3.1 8b Instruct: 33.0 (#209)
- StarCoder 2 3B: —

| Benchmark | Granite 3.1 8b Instruct | StarCoder 2 3B |
|---|---|---|
| LMArena Math | 1152 | — |
| GSM8K | — | 21.6% |

## Knowledge

- Granite 3.1 8b Instruct: 31.1 (#220)
- StarCoder 2 3B: —

| Benchmark | Granite 3.1 8b Instruct | StarCoder 2 3B |
|---|---|---|
| LMArena Expert | 1142 | — |
| ARC (AI2) Challenge | — | 34.2% |
| MMLU | — | 36.6% |

## Multilingual

- Granite 3.1 8b Instruct: 30.9 (#260)
- StarCoder 2 3B: —

| Benchmark | Granite 3.1 8b Instruct | StarCoder 2 3B |
|---|---|---|
| LMArena Non-English | 1099 | — |
| LMArena Chinese | 1145 | — |
| LMArena Russian | 1092 | — |

## Instruction Following

- Granite 3.1 8b Instruct: 58.6 (#259)
- StarCoder 2 3B: —

| Benchmark | Granite 3.1 8b Instruct | StarCoder 2 3B |
|---|---|---|
| LMArena Instruction Following | 1131 | — |

## Long Context

- Granite 3.1 8b Instruct: 35.2 (#241)
- StarCoder 2 3B: —

| Benchmark | Granite 3.1 8b Instruct | StarCoder 2 3B |
|---|---|---|
| LMArena Longer Query | 1162 | — |

## Writing & Preference

- Granite 3.1 8b Instruct: 35.5 (#266)
- StarCoder 2 3B: —

| Benchmark | Granite 3.1 8b Instruct | StarCoder 2 3B |
|---|---|---|
| LMArena Text | 1150 | — |
| LMArena Creative Writing | 1129 | — |
| LMArena Multi-Turn | 1108 | — |

## FAQ

### Is Granite 3.1 8b Instruct better than StarCoder 2 3B?

Granite 3.1 8b Instruct has enough public results to be ranked (#258); StarCoder 2 3B does not yet, so treat this comparison as directional.

### Is Granite 3.1 8b Instruct or StarCoder 2 3B better for coding?

Granite 3.1 8b Instruct scores higher on coding benchmarks: 34.5 versus 33.5 in the Noometry coding category.

### How many benchmarks do Granite 3.1 8b Instruct and StarCoder 2 3B share?

0 benchmarks have published results for both models. Granite 3.1 8b Instruct has 13 scored results on Noometry and StarCoder 2 3B has 7.
