# Granite 3.1 2b Instruct vs Qwen2.5 72B Instruct

> Granite 3.1 2b Instruct is the stronger model overall, scoring 33.2 to 31.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/granite-3-1-2b-instruct-vs-qwen2-5-72b-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 12

## Summary

- They share 12 benchmarks with published results for both. Granite 3.1 2b Instruct scores higher in 3 categories and Qwen2.5 72B Instruct in 5 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Granite 3.1 2b Instruct leads 33.1 to 19.3.

## Snapshot

| | Granite 3.1 2b Instruct | Qwen2.5 72B Instruct |
|---|---|---|
| Provider | IBM | Alibaba (Qwen) |
| Noometry Index | 33.2 | 31.9 |
| Rank | 247 | 267 |
| Context | — | 131K |
| Input $/M | — | $1.40 |
| Output $/M | — | $5.60 |
| Weights | Open | Open |

## Coding

- Granite 3.1 2b Instruct: 33.4 (#257)
- Qwen2.5 72B Instruct: 33.2 (#260)

| Benchmark | Granite 3.1 2b Instruct | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Coding | 1149 | 1292 |
| WeirdML | — | 16% |
| BigCodeBench Instruct | — | 45.8% |
| BigCodeBench Complete | — | 55.9% |

## Agentic & Tool Use

- Granite 3.1 2b Instruct: —
- Qwen2.5 72B Instruct: 22.1 (#133)

| Benchmark | Granite 3.1 2b Instruct | Qwen2.5 72B Instruct |
|---|---|---|
| TheAgentCompany | — | 5.7% |
| BALROG | — | 16.2% |
| METR Time Horizons | — | 35.8% |

## Reasoning

- Granite 3.1 2b Instruct: 22.0 (#209)
- Qwen2.5 72B Instruct: 22.3 (#199)

| Benchmark | Granite 3.1 2b Instruct | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1138 | 1271 |
| DTBench | — | 62.9% |
| LMCA | — | 13.4% |
| BIG-Bench Hard | — | 79.8% |
| Epoch Capabilities Index | — | 129 |
| ForecastBench | — | 57.5 |
| HellaSwag | — | 84.8% |
| PIQA | — | 82.6% |
| WinoGrande | — | 82.3% |

## Math

- Granite 3.1 2b Instruct: 33.1 (#206)
- Qwen2.5 72B Instruct: 19.3 (#287)

| Benchmark | Granite 3.1 2b Instruct | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Math | 1159 | 1283 |
| OTIS Mock AIME 2024-2025 | — | 8.1% |
| Omni-MATH | — | 33% |
| MATH Level 5 | — | 63.2% |

## Knowledge

- Granite 3.1 2b Instruct: 30.8 (#224)
- Qwen2.5 72B Instruct: 27.0 (#253)

| Benchmark | Granite 3.1 2b Instruct | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Expert | 1131 | 1245 |
| GPQA Diamond | — | 49.1% |
| MMLU-Pro | — | 63.1% |
| Confabulations | — | 19.1% |
| GPQA (HELM) | — | 42.6% |
| ARC (AI2) Challenge | — | 94.5% |
| MMLU | — | 85.3% |
| TriviaQA | — | 71.9% |

## Multilingual

- Granite 3.1 2b Instruct: 29.1 (#269)
- Qwen2.5 72B Instruct: 41.0 (#213)

| Benchmark | Granite 3.1 2b Instruct | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Non-English | 1068 | 1252 |
| LMArena Chinese | 1139 | 1272 |
| LMArena Russian | 1063 | 1264 |
| LMArena French | — | 1280 |
| LMArena German | — | 1234 |
| LMArena Japanese | — | 1180 |
| LMArena Korean | — | 1188 |
| LMArena Spanish | — | 1256 |

## Instruction Following

- Granite 3.1 2b Instruct: 57.7 (#264)
- Qwen2.5 72B Instruct: 65.5 (#221)

| Benchmark | Granite 3.1 2b Instruct | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Instruction Following | 1116 | 1254 |
| IFEval | — | 80.6% |

## Long Context

- Granite 3.1 2b Instruct: 35.0 (#244)
- Qwen2.5 72B Instruct: 38.9 (#188)

| Benchmark | Granite 3.1 2b Instruct | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Longer Query | 1155 | 1282 |

## Writing & Preference

- Granite 3.1 2b Instruct: 34.1 (#274)
- Qwen2.5 72B Instruct: 46.7 (#215)

| Benchmark | Granite 3.1 2b Instruct | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Text | 1127 | 1269 |
| LMArena Creative Writing | 1116 | 1221 |
| LMArena Multi-Turn | 1099 | 1272 |
| WildBench | — | 80.2% |

## FAQ

### Is Granite 3.1 2b Instruct better than Qwen2.5 72B Instruct?

Granite 3.1 2b Instruct is the stronger model overall, scoring 33.2 to 31.9 on the Noometry Index.

### Is Granite 3.1 2b Instruct or Qwen2.5 72B Instruct better for coding?

They score almost the same on coding (33.4 vs 33.2); test both on your own repository before choosing.

### How many benchmarks do Granite 3.1 2b Instruct and Qwen2.5 72B Instruct share?

12 benchmarks have published results for both models. Granite 3.1 2b Instruct has 12 scored results on Noometry and Qwen2.5 72B Instruct has 43.