# Granite 3.0 2b Instruct vs Mistral Large 3

> Mistral Large 3 is the stronger model overall, scoring 38.6 to 30.2 on the Noometry Index.

- Canonical page: https://noometry.com/compare/granite-3-0-2b-instruct-vs-mistral-large-3
- Last updated: 2026-10-10
- Shared benchmarks: 12

## Summary

- They share 12 benchmarks with published results for both. Granite 3.0 2b Instruct scores higher in 1 category and Mistral Large 3 in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Mistral Large 3 leads 60.2 to 29.8.

## Snapshot

| | Granite 3.0 2b Instruct | Mistral Large 3 |
|---|---|---|
| Provider | IBM | Mistral AI |
| Noometry Index | 30.2 | 38.6 |
| Rank | 284 | 172 |
| Context | — | 262K |
| Input $/M | — | $0.25 |
| Output $/M | — | $0.75 |
| Weights | Open | Open |

## Coding

- Granite 3.0 2b Instruct: 27.8 (#311)
- Mistral Large 3: 34.1 (#230)

| Benchmark | Granite 3.0 2b Instruct | Mistral Large 3 |
|---|---|---|
| LMArena Coding | 1090 | 1447 |
| LMArena WebDev | — | 1230 |
| BigCodeBench Instruct | 20.5% | — |

## Reasoning

- Granite 3.0 2b Instruct: 19.6 (#234)
- Mistral Large 3: 14.6 (#314)

| Benchmark | Granite 3.0 2b Instruct | Mistral Large 3 |
|---|---|---|
| LMArena Hard Prompts | 1073 | 1429 |
| Kagi LLM Benchmark | — | 50.9% |
| NYT Connections (extended) | — | 7.5% |
| Thematic Generalization | — | 23% |

## Math

- Granite 3.0 2b Instruct: 29.7 (#215)
- Mistral Large 3: 36.0 (#131)

| Benchmark | Granite 3.0 2b Instruct | Mistral Large 3 |
|---|---|---|
| LMArena Math | 1117 | 1415 |

## Knowledge

- Granite 3.0 2b Instruct: 28.4 (#238)
- Mistral Large 3: 35.5 (#173)

| Benchmark | Granite 3.0 2b Instruct | Mistral Large 3 |
|---|---|---|
| LMArena Expert | 1064 | 1421 |
| Vectara Hallucination Rate | — | 14.5% |

## Multimodal

- Granite 3.0 2b Instruct: —
- Mistral Large 3: 37.6 (#65)

| Benchmark | Granite 3.0 2b Instruct | Mistral Large 3 |
|---|---|---|
| LMArena Vision | — | 1222 |

## Multilingual

- Granite 3.0 2b Instruct: 27.1 (#273)
- Mistral Large 3: 52.6 (#79)

| Benchmark | Granite 3.0 2b Instruct | Mistral Large 3 |
|---|---|---|
| LMArena Non-English | 1033 | 1412 |
| LMArena Chinese | 1070 | 1448 |
| LMArena Russian | 1045 | 1412 |
| LMArena French | — | 1456 |
| LMArena German | — | 1438 |
| LMArena Japanese | — | 1399 |
| LMArena Korean | — | 1384 |
| LMArena Spanish | — | 1437 |

## Instruction Following

- Granite 3.0 2b Instruct: 54.2 (#279)
- Mistral Large 3: 74.1 (#104)

| Benchmark | Granite 3.0 2b Instruct | Mistral Large 3 |
|---|---|---|
| LMArena Instruction Following | 1056 | 1402 |

## Long Context

- Granite 3.0 2b Instruct: 32.5 (#263)
- Mistral Large 3: 43.1 (#102)

| Benchmark | Granite 3.0 2b Instruct | Mistral Large 3 |
|---|---|---|
| LMArena Longer Query | 1071 | 1413 |

## Writing & Preference

- Granite 3.0 2b Instruct: 29.8 (#287)
- Mistral Large 3: 60.2 (#100)

| Benchmark | Granite 3.0 2b Instruct | Mistral Large 3 |
|---|---|---|
| LMArena Text | 1080 | 1427 |
| LMArena Creative Writing | 1046 | 1385 |
| LMArena Multi-Turn | 1053 | 1429 |
| EQ-Bench Creative Writing | — | 1412 |

## FAQ

### Is Granite 3.0 2b Instruct better than Mistral Large 3?

Mistral Large 3 is the stronger model overall, scoring 38.6 to 30.2 on the Noometry Index.

### Is Granite 3.0 2b Instruct or Mistral Large 3 better for coding?

Mistral Large 3 scores higher on coding benchmarks: 34.1 versus 27.8 in the Noometry coding category.

### How many benchmarks do Granite 3.0 2b Instruct and Mistral Large 3 share?

12 benchmarks have published results for both models. Granite 3.0 2b Instruct has 13 scored results on Noometry and Mistral Large 3 has 24.