# Granite 3.0 2b Instruct vs Qwen3 8B

> Qwen3 8B is the stronger model overall, scoring 33.3 to 30.2 on the Noometry Index.

- Canonical page: https://noometry.com/compare/granite-3-0-2b-instruct-vs-qwen3-8b
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in knowledge, where Qwen3 8B leads 36.1 to 28.4.

## Snapshot

| | Granite 3.0 2b Instruct | Qwen3 8B |
|---|---|---|
| Provider | IBM | Alibaba (Qwen) |
| Noometry Index | 30.2 | 33.3 |
| Rank | 284 | 237 |
| Context | — | 131K |
| Input $/M | — | $0.18 |
| Output $/M | — | $0.70 |
| Weights | Open | Open |

## Coding

- Granite 3.0 2b Instruct: 27.8 (#311)
- Qwen3 8B: 33.4 (#245)

| Benchmark | Granite 3.0 2b Instruct | Qwen3 8B |
|---|---|---|
| SciCode | — | 22.6% |
| BigCodeBench Instruct | 20.5% | — |
| LMArena Coding | 1090 | — |

## Agentic & Tool Use

- Granite 3.0 2b Instruct: —
- Qwen3 8B: 29.9 (#71)

| Benchmark | Granite 3.0 2b Instruct | Qwen3 8B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 42.6% |

## Reasoning

- Granite 3.0 2b Instruct: 19.6 (#234)
- Qwen3 8B: 16.1 (#299)

| Benchmark | Granite 3.0 2b Instruct | Qwen3 8B |
|---|---|---|
| CritPt | — | 0% |
| Chess Puzzles | — | 5% |
| LMArena Hard Prompts | 1073 | — |
| DTBench | — | 59.7% |
| LMCA | — | 8.8% |
| Epoch Capabilities Index | — | 136.17 |

## Math

- Granite 3.0 2b Instruct: 29.7 (#215)
- Qwen3 8B: 33.3 (#176)

| Benchmark | Granite 3.0 2b Instruct | Qwen3 8B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 56.1% |
| LMArena Math | 1117 | — |

## Knowledge

- Granite 3.0 2b Instruct: 28.4 (#238)
- Qwen3 8B: 36.1 (#164)

| Benchmark | Granite 3.0 2b Instruct | Qwen3 8B |
|---|---|---|
| GPQA Diamond | — | 56.8% |
| Vectara Hallucination Rate | — | 4.8% |
| LMArena Expert | 1064 | — |

## Multilingual

- Granite 3.0 2b Instruct: 27.1 (#273)
- Qwen3 8B: —

| Benchmark | Granite 3.0 2b Instruct | Qwen3 8B |
|---|---|---|
| LMArena Non-English | 1033 | — |
| LMArena Chinese | 1070 | — |
| LMArena Russian | 1045 | — |

## Instruction Following

- Granite 3.0 2b Instruct: 54.2 (#279)
- Qwen3 8B: —

| Benchmark | Granite 3.0 2b Instruct | Qwen3 8B |
|---|---|---|
| LMArena Instruction Following | 1056 | — |

## Long Context

- Granite 3.0 2b Instruct: 32.5 (#263)
- Qwen3 8B: 37.8 (#205)

| Benchmark | Granite 3.0 2b Instruct | Qwen3 8B |
|---|---|---|
| Fiction.LiveBench | — | 62.1% |
| LMArena Longer Query | 1071 | — |

## Writing & Preference

- Granite 3.0 2b Instruct: 29.8 (#287)
- Qwen3 8B: —

| Benchmark | Granite 3.0 2b Instruct | Qwen3 8B |
|---|---|---|
| LMArena Text | 1080 | — |
| LMArena Creative Writing | 1046 | — |
| LMArena Multi-Turn | 1053 | — |

## FAQ

### Is Granite 3.0 2b Instruct better than Qwen3 8B?

Qwen3 8B is the stronger model overall, scoring 33.3 to 30.2 on the Noometry Index.

### Is Granite 3.0 2b Instruct or Qwen3 8B better for coding?

Qwen3 8B scores higher on coding benchmarks: 33.4 versus 27.8 in the Noometry coding category.

### How many benchmarks do Granite 3.0 2b Instruct and Qwen3 8B share?

0 benchmarks have published results for both models. Granite 3.0 2b Instruct has 13 scored results on Noometry and Qwen3 8B has 11.