# Granite 4.2 30b vs Mistral Small

> Granite 4.2 30b is the stronger model overall, scoring 41.8 to 33.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/granite-4-2-30b-vs-mistral-small
- Last updated: 2026-10-11
- Shared benchmarks: 11

## Summary

- They share 11 benchmarks with published results for both. Granite 4.2 30b scores higher in 7 categories and Mistral Small in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Granite 4.2 30b leads 39.1 to 31.0.

## Snapshot

| | Granite 4.2 30b | Mistral Small |
|---|---|---|
| Provider | IBM | Mistral AI |
| Noometry Index | 41.8 | 33.4 |
| Rank | 130 | 243 |
| Context | — | 262K |
| Input $/M | — | $0.15 |
| Output $/M | — | $0.60 |
| Weights | Open | Open |

## Coding

- Granite 4.2 30b: 41.0 (#126)
- Mistral Small: 34.0 (#247)

| Benchmark | Granite 4.2 30b | Mistral Small |
|---|---|---|
| LMArena Coding | 1396 | 1362 |
| SciCode | — | 26.5% |
| BigCodeBench Instruct | — | 36.1% |
| LiveBench Coding | — | 36.2% |
| BigCodeBench Complete | — | 46.6% |
| ALE-Bench | — | 497.62 |

## Agentic & Tool Use

- Granite 4.2 30b: —
- Mistral Small: 28.1 (#93)

| Benchmark | Granite 4.2 30b | Mistral Small |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 37.1% |

## Reasoning

- Granite 4.2 30b: 27.8 (#112)
- Mistral Small: 19.8 (#250)

| Benchmark | Granite 4.2 30b | Mistral Small |
|---|---|---|
| LMArena Hard Prompts | 1374 | 1335 |
| Kagi LLM Benchmark | — | 37.8% |
| CritPt | — | 0% |
| LiveBench Reasoning | — | 44.8% |
| DTBench | — | 70.9% |
| LiveBench Data Analysis | — | 53.7% |
| LMCA | — | 20.6% |
| LiveBench | — | 44% |

## Math

- Granite 4.2 30b: —
- Mistral Small: 16.4 (#293)

| Benchmark | Granite 4.2 30b | Mistral Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 5.8% |
| LiveBench Math | — | 39.9% |
| LMArena Math | — | 1341 |
| MATH Level 5 | — | 46.8% |

## Knowledge

- Granite 4.2 30b: 39.1 (#138)
- Mistral Small: 31.0 (#222)

| Benchmark | Granite 4.2 30b | Mistral Small |
|---|---|---|
| LMArena Expert | 1406 | 1291 |
| GPQA Diamond | — | 47.5% |
| Vectara Hallucination Rate | — | 5.1% |
| MMLU | — | 68.7% |

## Multimodal

- Granite 4.2 30b: —
- Mistral Small: 33.5 (#96)

| Benchmark | Granite 4.2 30b | Mistral Small |
|---|---|---|
| LMArena Vision | — | 1142 |

## Multilingual

- Granite 4.2 30b: 47.3 (#151)
- Mistral Small: 45.5 (#169)

| Benchmark | Granite 4.2 30b | Mistral Small |
|---|---|---|
| LMArena Non-English | 1340 | 1315 |
| LMArena Chinese | 1414 | 1340 |
| LMArena Russian | 1343 | 1324 |
| LMArena French | — | 1337 |
| LMArena German | — | 1340 |
| LMArena Japanese | — | 1275 |
| LMArena Korean | — | 1259 |
| LMArena Spanish | — | 1346 |

## Instruction Following

- Granite 4.2 30b: 71.2 (#155)
- Mistral Small: 66.4 (#209)

| Benchmark | Granite 4.2 30b | Mistral Small |
|---|---|---|
| LMArena Instruction Following | 1347 | 1310 |
| LiveBench Instruction Following | — | 63.7% |

## Long Context

- Granite 4.2 30b: 41.4 (#140)
- Mistral Small: 40.4 (#156)

| Benchmark | Granite 4.2 30b | Mistral Small |
|---|---|---|
| LMArena Longer Query | 1359 | 1327 |

## Writing & Preference

- Granite 4.2 30b: 53.8 (#156)
- Mistral Small: 52.5 (#171)

| Benchmark | Granite 4.2 30b | Mistral Small |
|---|---|---|
| LMArena Text | 1361 | 1338 |
| LMArena Creative Writing | 1288 | 1305 |
| LMArena Multi-Turn | 1339 | 1344 |
| LiveBench Language | — | 30.5% |

## FAQ

### Is Granite 4.2 30b better than Mistral Small?

Granite 4.2 30b is the stronger model overall, scoring 41.8 to 33.4 on the Noometry Index.

### Is Granite 4.2 30b or Mistral Small better for coding?

Granite 4.2 30b scores higher on coding benchmarks: 41.0 versus 34.0 in the Noometry coding category.

### How many benchmarks do Granite 4.2 30b and Mistral Small share?

11 benchmarks have published results for both models. Granite 4.2 30b has 11 scored results on Noometry and Mistral Small has 39.