# Granite 3.1 8b Instruct vs Yi-34B

> Granite 3.1 8b Instruct is the stronger model overall, scoring 31.8 to 27.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/granite-3-1-8b-instruct-vs-yi-34b
- 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 8 categories and Yi-34B in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Granite 3.1 8b Instruct leads 30.6 to 7.5.

## Snapshot

| | Granite 3.1 8b Instruct | Yi-34B |
|---|---|---|
| Provider | IBM | 01.AI |
| Noometry Index | 31.8 | 27.4 |
| Rank | 256 | 325 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- Granite 3.1 8b Instruct: 33.9 (#232)
- Yi-34B: 31.8 (#269)

| Benchmark | Granite 3.1 8b Instruct | Yi-34B |
|---|---|---|
| LMArena Coding | 1186 | 1112 |

## Agentic & Tool Use

- Granite 3.1 8b Instruct: 23.9 (#113)
- Yi-34B: —

| Benchmark | Granite 3.1 8b Instruct | Yi-34B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 27.1% | — |

## Reasoning

- Granite 3.1 8b Instruct: 21.2 (#204)
- Yi-34B: 20.3 (#222)

| Benchmark | Granite 3.1 8b Instruct | Yi-34B |
|---|---|---|
| LMArena Hard Prompts | 1146 | 1104 |
| BIG-Bench Hard | — | 71.7% |
| Epoch Capabilities Index | — | 117.28 |

## Math

- Granite 3.1 8b Instruct: 30.4 (#210)
- Yi-34B: 19.8 (#277)

| Benchmark | Granite 3.1 8b Instruct | Yi-34B |
|---|---|---|
| LMArena Math | 1152 | 1114 |
| MATH Level 5 | — | 5.1% |
| GSM8K | — | 76% |

## Knowledge

- Granite 3.1 8b Instruct: 30.6 (#218)
- Yi-34B: 7.5 (#304)

| Benchmark | Granite 3.1 8b Instruct | Yi-34B |
|---|---|---|
| LMArena Expert | 1142 | 1061 |
| GPQA Diamond | — | 14.7% |
| MMLU | — | 76.3% |

## Multilingual

- Granite 3.1 8b Instruct: 31.1 (#255)
- Yi-34B: 29.9 (#259)

| Benchmark | Granite 3.1 8b Instruct | Yi-34B |
|---|---|---|
| LMArena Non-English | 1099 | 1079 |
| LMArena Chinese | 1145 | 1175 |
| LMArena Russian | 1092 | 1050 |
| LMArena French | — | 1080 |
| LMArena German | — | 1042 |
| LMArena Japanese | — | 993 |
| LMArena Korean | — | 959 |
| LMArena Spanish | — | 1070 |

## Instruction Following

- Granite 3.1 8b Instruct: 58.9 (#254)
- Yi-34B: 56.4 (#269)

| Benchmark | Granite 3.1 8b Instruct | Yi-34B |
|---|---|---|
| LMArena Instruction Following | 1131 | 1091 |

## Long Context

- Granite 3.1 8b Instruct: 35.2 (#236)
- Yi-34B: 33.2 (#259)

| Benchmark | Granite 3.1 8b Instruct | Yi-34B |
|---|---|---|
| LMArena Longer Query | 1162 | 1094 |

## Writing & Preference

- Granite 3.1 8b Instruct: 35.7 (#261)
- Yi-34B: 34.3 (#268)

| Benchmark | Granite 3.1 8b Instruct | Yi-34B |
|---|---|---|
| LMArena Text | 1150 | 1129 |
| LMArena Creative Writing | 1129 | 1108 |
| LMArena Multi-Turn | 1108 | 1113 |

## FAQ

### Is Granite 3.1 8b Instruct better than Yi-34B?

Granite 3.1 8b Instruct is the stronger model overall, scoring 31.8 to 27.4 on the Noometry Index.

### Is Granite 3.1 8b Instruct or Yi-34B better for coding?

Granite 3.1 8b Instruct scores higher on coding benchmarks: 33.9 versus 31.8 in the Noometry coding category.

### How many benchmarks do Granite 3.1 8b Instruct and Yi-34B share?

12 benchmarks have published results for both models. Granite 3.1 8b Instruct has 13 scored results on Noometry and Yi-34B has 23.