# Granite 3.0 2b Instruct vs Mistral Large

> Mistral Large is the stronger model overall, scoring 31.9 to 30.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/granite-3-0-2b-instruct-vs-mistral-large
- Last updated: 2026-10-10
- Shared benchmarks: 13

## Summary

- They share 13 benchmarks with published results for both. Granite 3.0 2b Instruct scores higher in 2 categories and Mistral Large in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Granite 3.0 2b Instruct leads 32.2 to 18.2.
- The biggest single-benchmark swing is BigCodeBench Instruct: 20.5% for Granite 3.0 2b Instruct and 30% for Mistral Large.

## Snapshot

| | Granite 3.0 2b Instruct | Mistral Large |
|---|---|---|
| Provider | IBM | Mistral AI |
| Noometry Index | 30.8 | 31.9 |
| Rank | 286 | 263 |
| Context | — | 131K |
| Input $/M | — | $2 |
| Output $/M | — | $6 |
| Weights | Open | Open |

## Coding

- Granite 3.0 2b Instruct: 28.3 (#316)
- Mistral Large: 34.3 (#240)

| Benchmark | Granite 3.0 2b Instruct | Mistral Large |
|---|---|---|
| BigCodeBench Instruct | 20.5% | 30% |
| LMArena Coding | 1090 | 1277 |
| SciCode | — | 36.2% |
| LiveBench Coding | — | 47.1% |
| BigCodeBench Complete | — | 38.3% |
| ALE-Bench | — | 264.7 |
| HumanEval+ | — | 62.2% |
| MBPP+ | — | 59.5% |

## Agentic & Tool Use

- Granite 3.0 2b Instruct: —
- Mistral Large: 28.6 (#89)

| Benchmark | Granite 3.0 2b Instruct | Mistral Large |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 38.4% |

## Reasoning

- Granite 3.0 2b Instruct: 20.5 (#235)
- Mistral Large: 15.8 (#310)

| Benchmark | Granite 3.0 2b Instruct | Mistral Large |
|---|---|---|
| LMArena Hard Prompts | 1073 | 1257 |
| SimpleBench | — | 22.5% |
| CritPt | — | 0% |
| LiveBench Reasoning | — | 43.5% |
| DTBench | — | 65.1% |
| LiveBench Data Analysis | — | 50.1% |
| LMCA | — | 16.7% |
| Epoch Capabilities Index | — | 128.52 |
| ForecastBench | — | 57.1 |
| LiveBench | — | 48.4% |

## Math

- Granite 3.0 2b Instruct: 32.2 (#217)
- Mistral Large: 18.2 (#291)

| Benchmark | Granite 3.0 2b Instruct | Mistral Large |
|---|---|---|
| LMArena Math | 1117 | 1262 |
| OTIS Mock AIME 2024-2025 | — | 8.5% |
| Omni-MATH | — | 28.1% |
| LiveBench Math | — | 42.5% |
| MATH Level 5 | — | 50.3% |
| FrontierMath (Feb 2025 set) | — | 0.3% |

## Knowledge

- Granite 3.0 2b Instruct: 29.0 (#241)
- Mistral Large: 30.1 (#230)

| Benchmark | Granite 3.0 2b Instruct | Mistral Large |
|---|---|---|
| LMArena Expert | 1064 | 1232 |
| GPQA Diamond | — | 51.3% |
| MMLU-Pro | — | 59.9% |
| Confabulations | — | 21.4% |
| Vectara Hallucination Rate | — | 4.5% |
| GPQA (HELM) | — | 43.5% |
| MMLU | — | 80% |

## Multilingual

- Granite 3.0 2b Instruct: 27.0 (#278)
- Mistral Large: 40.0 (#219)

| Benchmark | Granite 3.0 2b Instruct | Mistral Large |
|---|---|---|
| LMArena Non-English | 1033 | 1237 |
| LMArena Chinese | 1070 | 1240 |
| LMArena Russian | 1045 | 1257 |
| LMArena French | — | 1325 |
| LMArena German | — | 1254 |
| LMArena Japanese | — | 1188 |
| LMArena Korean | — | 1202 |
| LMArena Spanish | — | 1268 |

## Instruction Following

- Granite 3.0 2b Instruct: 53.9 (#284)
- Mistral Large: 67.9 (#191)

| Benchmark | Granite 3.0 2b Instruct | Mistral Large |
|---|---|---|
| LMArena Instruction Following | 1056 | 1249 |
| LiveBench Instruction Following | — | 67.9% |
| IFEval | — | 87.7% |

## Long Context

- Granite 3.0 2b Instruct: 32.5 (#268)
- Mistral Large: 38.3 (#199)

| Benchmark | Granite 3.0 2b Instruct | Mistral Large |
|---|---|---|
| LMArena Longer Query | 1070 | 1261 |

## Writing & Preference

- Granite 3.0 2b Instruct: 29.6 (#292)
- Mistral Large: 40.7 (#242)

| Benchmark | Granite 3.0 2b Instruct | Mistral Large |
|---|---|---|
| LMArena Text | 1080 | 1266 |
| LMArena Creative Writing | 1046 | 1243 |
| LMArena Multi-Turn | 1053 | 1260 |
| Short-Story Creative Writing | — | 69% |
| EQ-Bench Creative Writing | — | 985 |
| WildBench | — | 80.1% |
| LiveBench Language | — | 39.4% |

## FAQ

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

Mistral Large is the stronger model overall, scoring 31.9 to 30.8 on the Noometry Index.

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

Mistral Large scores higher on coding benchmarks: 34.3 versus 28.3 in the Noometry coding category.

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

13 benchmarks have published results for both models. Granite 3.0 2b Instruct has 13 scored results on Noometry and Mistral Large has 51.