# DeepSeek Coder 6.7B vs Granite 4.0 H Small

> Granite 4.0 H Small has enough public results to be ranked (#213); DeepSeek Coder 6.7B does not yet, so treat this comparison as directional.

- Canonical page: https://noometry.com/compare/deepseek-coder-6-7b-vs-ibm-granite-h-small
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Snapshot

| | DeepSeek Coder 6.7B | Granite 4.0 H Small |
|---|---|---|
| Provider | DeepSeek | IBM |
| Noometry Index | 37.1 | 35.9 |
| Rank | — | 213 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- DeepSeek Coder 6.7B: 35.2 (#216)
- Granite 4.0 H Small: 35.8 (#207)

| Benchmark | DeepSeek Coder 6.7B | Granite 4.0 H Small |
|---|---|---|
| BigCodeBench Instruct | 35.5% | — |
| LMArena Coding | — | 1247 |
| BigCodeBench Complete | 43.8% | — |
| HumanEval+ | 71.3% | — |
| MBPP+ | 65.6% | — |

## Reasoning

- DeepSeek Coder 6.7B: —
- Granite 4.0 H Small: 23.4 (#164)

| Benchmark | DeepSeek Coder 6.7B | Granite 4.0 H Small |
|---|---|---|
| LMArena Hard Prompts | — | 1240 |
| Epoch Capabilities Index | 88.88 | — |
| WinoGrande | 57.6% | — |

## Math

- DeepSeek Coder 6.7B: —
- Granite 4.0 H Small: 29.3 (#219)

| Benchmark | DeepSeek Coder 6.7B | Granite 4.0 H Small |
|---|---|---|
| Omni-MATH | — | 29.6% |
| LMArena Math | — | 1251 |
| GSM8K | 21.3% | — |

## Knowledge

- DeepSeek Coder 6.7B: —
- Granite 4.0 H Small: 31.5 (#210)

| Benchmark | DeepSeek Coder 6.7B | Granite 4.0 H Small |
|---|---|---|
| MMLU-Pro | — | 56.9% |
| Vectara Hallucination Rate | — | 5.2% |
| GPQA (HELM) | — | 38.3% |
| LMArena Expert | — | 1244 |
| ARC (AI2) Challenge | 36.4% | — |
| MMLU | 36.4% | — |

## Multilingual

- DeepSeek Coder 6.7B: —
- Granite 4.0 H Small: 38.7 (#223)

| Benchmark | DeepSeek Coder 6.7B | Granite 4.0 H Small |
|---|---|---|
| LMArena Non-English | — | 1216 |
| LMArena Chinese | — | 1250 |
| LMArena Russian | — | 1198 |
| LMArena Spanish | — | 1258 |

## Instruction Following

- DeepSeek Coder 6.7B: —
- Granite 4.0 H Small: 68.9 (#178)

| Benchmark | DeepSeek Coder 6.7B | Granite 4.0 H Small |
|---|---|---|
| IFEval | — | 89% |
| LMArena Instruction Following | — | 1221 |

## Long Context

- DeepSeek Coder 6.7B: —
- Granite 4.0 H Small: 37.6 (#209)

| Benchmark | DeepSeek Coder 6.7B | Granite 4.0 H Small |
|---|---|---|
| LMArena Longer Query | — | 1240 |

## Writing & Preference

- DeepSeek Coder 6.7B: —
- Granite 4.0 H Small: 44.0 (#222)

| Benchmark | DeepSeek Coder 6.7B | Granite 4.0 H Small |
|---|---|---|
| LMArena Text | — | 1241 |
| LMArena Creative Writing | — | 1210 |
| WildBench | — | 73.9% |
| LMArena Multi-Turn | — | 1243 |

## FAQ

### Is DeepSeek Coder 6.7B better than Granite 4.0 H Small?

Granite 4.0 H Small has enough public results to be ranked (#213); DeepSeek Coder 6.7B does not yet, so treat this comparison as directional.

### Is DeepSeek Coder 6.7B or Granite 4.0 H Small better for coding?

They score almost the same on coding (35.2 vs 35.8); test both on your own repository before choosing.

### How many benchmarks do DeepSeek Coder 6.7B and Granite 4.0 H Small share?

0 benchmarks have published results for both models. DeepSeek Coder 6.7B has 9 scored results on Noometry and Granite 4.0 H Small has 19.