# Granite 4.2 8B vs Mistral Large 3

> Granite 4.2 8B is the stronger model overall, scoring 40.0 to 38.6 on the Noometry Index.

- Canonical page: https://noometry.com/compare/granite-4-2-8b-vs-mistral-large-3
- Last updated: 2026-10-10
- Shared benchmarks: 11

## Summary

- They share 11 benchmarks with published results for both. Granite 4.2 8B scores higher in 3 categories and Mistral Large 3 in 4 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Granite 4.2 8B leads 25.5 to 14.6.
- Granite 4.2 8B is cheaper at $0.06 / $0.25 per million input/output tokens, against $0.25 / $0.75 for Mistral Large 3.
- Mistral Large 3 accepts more context: 262K tokens versus 131K.

## Snapshot

| | Granite 4.2 8B | Mistral Large 3 |
|---|---|---|
| Provider | IBM | Mistral AI |
| Noometry Index | 40.0 | 38.6 |
| Rank | 143 | 172 |
| Context | 131K | 262K |
| Input $/M | $0.06 | $0.25 |
| Output $/M | $0.25 | $0.75 |
| Weights | Open | Open |

## Coding

- Granite 4.2 8B: 39.9 (#138)
- Mistral Large 3: 34.1 (#230)

| Benchmark | Granite 4.2 8B | Mistral Large 3 |
|---|---|---|
| LMArena Coding | 1379 | 1447 |
| LMArena WebDev | — | 1230 |

## Reasoning

- Granite 4.2 8B: 25.5 (#130)
- Mistral Large 3: 14.6 (#314)

| Benchmark | Granite 4.2 8B | Mistral Large 3 |
|---|---|---|
| LMArena Hard Prompts | 1327 | 1429 |
| Kagi LLM Benchmark | — | 50.9% |
| NYT Connections (extended) | — | 7.5% |
| Thematic Generalization | — | 23% |

## Math

- Granite 4.2 8B: —
- Mistral Large 3: 36.0 (#131)

| Benchmark | Granite 4.2 8B | Mistral Large 3 |
|---|---|---|
| LMArena Math | — | 1415 |

## Knowledge

- Granite 4.2 8B: 37.7 (#144)
- Mistral Large 3: 35.5 (#173)

| Benchmark | Granite 4.2 8B | Mistral Large 3 |
|---|---|---|
| LMArena Expert | 1380 | 1421 |
| Vectara Hallucination Rate | — | 14.5% |

## Multimodal

- Granite 4.2 8B: —
- Mistral Large 3: 37.6 (#65)

| Benchmark | Granite 4.2 8B | Mistral Large 3 |
|---|---|---|
| LMArena Vision | — | 1222 |

## Multilingual

- Granite 4.2 8B: 44.5 (#173)
- Mistral Large 3: 52.6 (#79)

| Benchmark | Granite 4.2 8B | Mistral Large 3 |
|---|---|---|
| LMArena Non-English | 1299 | 1412 |
| LMArena Chinese | 1361 | 1448 |
| LMArena Russian | 1283 | 1412 |
| LMArena French | — | 1456 |
| LMArena German | — | 1438 |
| LMArena Japanese | — | 1399 |
| LMArena Korean | — | 1384 |
| LMArena Spanish | — | 1437 |

## Instruction Following

- Granite 4.2 8B: 68.7 (#183)
- Mistral Large 3: 74.1 (#104)

| Benchmark | Granite 4.2 8B | Mistral Large 3 |
|---|---|---|
| LMArena Instruction Following | 1298 | 1402 |

## Long Context

- Granite 4.2 8B: 40.2 (#154)
- Mistral Large 3: 43.1 (#102)

| Benchmark | Granite 4.2 8B | Mistral Large 3 |
|---|---|---|
| LMArena Longer Query | 1323 | 1413 |

## Writing & Preference

- Granite 4.2 8B: 49.8 (#183)
- Mistral Large 3: 60.2 (#100)

| Benchmark | Granite 4.2 8B | Mistral Large 3 |
|---|---|---|
| LMArena Text | 1319 | 1427 |
| LMArena Creative Writing | 1238 | 1385 |
| LMArena Multi-Turn | 1299 | 1429 |
| EQ-Bench Creative Writing | — | 1412 |

## FAQ

### Is Granite 4.2 8B better than Mistral Large 3?

Granite 4.2 8B is the stronger model overall, scoring 40.0 to 38.6 on the Noometry Index.

### Which is cheaper, Granite 4.2 8B or Mistral Large 3?

Granite 4.2 8B is cheaper. It lists at $0.06 per million input tokens and $0.25 per million output tokens; Mistral Large 3 lists at $0.25 and $0.75.

### Is Granite 4.2 8B or Mistral Large 3 better for coding?

Granite 4.2 8B scores higher on coding benchmarks: 39.9 versus 34.1 in the Noometry coding category.

### Which has the bigger context window?

Mistral Large 3 does, with 262K tokens against 131K.

### How many benchmarks do Granite 4.2 8B and Mistral Large 3 share?

11 benchmarks have published results for both models. Granite 4.2 8B has 11 scored results on Noometry and Mistral Large 3 has 24.