# Granite 3.1 8b Instruct vs Grok-2 (Dec 2024)

> Grok-2 (Dec 2024) is the stronger model overall, scoring 33.4 to 31.8 on the Noometry Index.

- Canonical page: https://noometry.com/compare/granite-3-1-8b-instruct-vs-grok-2
- Last updated: 2026-10-10
- Shared benchmarks: 12

## Summary

- They share 12 benchmarks with published results for both. Granite 3.1 8b Instruct scores higher in 4 categories and Grok-2 (Dec 2024) in 4 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Grok-2 (Dec 2024) leads 48.8 to 35.7.
- Granite 3.1 8b Instruct has downloadable open weights; the other is API-only.

## Snapshot

| | Granite 3.1 8b Instruct | Grok-2 (Dec 2024) |
|---|---|---|
| Provider | IBM | xAI |
| Noometry Index | 31.8 | 33.4 |
| Rank | 256 | 233 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Proprietary |

## Coding

- Granite 3.1 8b Instruct: 33.9 (#232)
- Grok-2 (Dec 2024): 32.9 (#254)

| Benchmark | Granite 3.1 8b Instruct | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Coding | 1186 | 1288 |
| WeirdML | — | 22.2% |
| LiveBench Coding | — | 46.4% |

## Agentic & Tool Use

- Granite 3.1 8b Instruct: 23.9 (#113)
- Grok-2 (Dec 2024): —

| Benchmark | Granite 3.1 8b Instruct | Grok-2 (Dec 2024) |
|---|---|---|
| Berkeley Function Calling Leaderboard | 27.1% | — |

## Reasoning

- Granite 3.1 8b Instruct: 21.2 (#204)
- Grok-2 (Dec 2024): 16.4 (#294)

| Benchmark | Granite 3.1 8b Instruct | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Hard Prompts | 1146 | 1272 |
| SimpleBench | — | 22.7% |
| LiveBench Reasoning | — | 54.8% |
| DTBench | — | 65.2% |
| LiveBench Data Analysis | — | 54.5% |
| Epoch Capabilities Index | — | 130.48 |
| LiveBench | — | 54.3% |

## Math

- Granite 3.1 8b Instruct: 30.4 (#210)
- Grok-2 (Dec 2024): 19.6 (#278)

| Benchmark | Granite 3.1 8b Instruct | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Math | 1152 | 1283 |
| OTIS Mock AIME 2024-2025 | — | 11.5% |
| LiveBench Math | — | 54.9% |
| MATH Level 5 | — | 63.5% |
| FrontierMath (Feb 2025 set) | — | 0.7% |

## Knowledge

- Granite 3.1 8b Instruct: 30.6 (#218)
- Grok-2 (Dec 2024): 29.8 (#225)

| Benchmark | Granite 3.1 8b Instruct | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Expert | 1142 | 1254 |
| GPQA Diamond | — | 53.8% |
| Confabulations | — | 20.1% |

## Multilingual

- Granite 3.1 8b Instruct: 31.1 (#255)
- Grok-2 (Dec 2024): 43.3 (#183)

| Benchmark | Granite 3.1 8b Instruct | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Non-English | 1099 | 1282 |
| LMArena Chinese | 1145 | 1289 |
| LMArena Russian | 1092 | 1286 |
| LMArena French | — | 1317 |
| LMArena German | — | 1287 |
| LMArena Japanese | — | 1244 |
| LMArena Korean | — | 1237 |
| LMArena Spanish | — | 1281 |

## Instruction Following

- Granite 3.1 8b Instruct: 58.9 (#254)
- Grok-2 (Dec 2024): 67.1 (#197)

| Benchmark | Granite 3.1 8b Instruct | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Instruction Following | 1131 | 1270 |
| LiveBench Instruction Following | — | 69.6% |

## Long Context

- Granite 3.1 8b Instruct: 35.2 (#236)
- Grok-2 (Dec 2024): 38.7 (#186)

| Benchmark | Granite 3.1 8b Instruct | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Longer Query | 1162 | 1276 |

## Writing & Preference

- Granite 3.1 8b Instruct: 35.7 (#261)
- Grok-2 (Dec 2024): 48.8 (#192)

| Benchmark | Granite 3.1 8b Instruct | Grok-2 (Dec 2024) |
|---|---|---|
| LMArena Text | 1150 | 1305 |
| LMArena Creative Writing | 1129 | 1284 |
| LMArena Multi-Turn | 1108 | 1290 |
| Short-Story Creative Writing | — | 63.6% |
| LiveBench Language | — | 45.6% |

## FAQ

### Is Granite 3.1 8b Instruct better than Grok-2 (Dec 2024)?

Grok-2 (Dec 2024) is the stronger model overall, scoring 33.4 to 31.8 on the Noometry Index.

### Is Granite 3.1 8b Instruct or Grok-2 (Dec 2024) better for coding?

Granite 3.1 8b Instruct scores higher on coding benchmarks: 33.9 versus 32.9 in the Noometry coding category.

### How many benchmarks do Granite 3.1 8b Instruct and Grok-2 (Dec 2024) share?

12 benchmarks have published results for both models. Granite 3.1 8b Instruct has 13 scored results on Noometry and Grok-2 (Dec 2024) has 34.