# DeepSeek-V2.5 (Sep 2024) vs Granite 4.1 8b

> DeepSeek-V2.5 (Sep 2024) and Granite 4.1 8b score almost the same on the Noometry Index (37.6 vs 37.4), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/deepseek-v2-5-vs-granite-4-1-8b
- Last updated: 2026-10-12
- Shared benchmarks: 12

## Summary

- They share 12 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 5 categories and Granite 4.1 8b in 3 categories; 3 gaps are clear of the uncertainty.

## Snapshot

| | DeepSeek-V2.5 (Sep 2024) | Granite 4.1 8b |
|---|---|---|
| Provider | DeepSeek | IBM |
| Noometry Index | 37.6 | 37.4 |
| Rank | 200 | 205 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Open | Open |

## Coding

- DeepSeek-V2.5 (Sep 2024): 31.7 (#281)
- Granite 4.1 8b: 30.1 (#297)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Granite 4.1 8b |
|---|---|---|
| LMArena Coding | 1309 | 1312 |
| Aider Polyglot | 17.8% | — |
| LMArena WebDev | — | 1192 |
| BigCodeBench Instruct | 48.6% | — |
| BigCodeBench Complete | 53.2% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |

## Reasoning

- DeepSeek-V2.5 (Sep 2024): 25.6 (#145)
- Granite 4.1 8b: 25.7 (#143)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Granite 4.1 8b |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1293 |

## Math

- DeepSeek-V2.5 (Sep 2024): 35.9 (#177)
- Granite 4.1 8b: 36.4 (#166)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Granite 4.1 8b |
|---|---|---|
| LMArena Math | 1288 | 1312 |

## Knowledge

- DeepSeek-V2.5 (Sep 2024): 34.8 (#193)
- Granite 4.1 8b: 36.1 (#174)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Granite 4.1 8b |
|---|---|---|
| LMArena Expert | 1266 | 1309 |

## Multilingual

- DeepSeek-V2.5 (Sep 2024): 42.5 (#193)
- Granite 4.1 8b: 41.7 (#204)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Granite 4.1 8b |
|---|---|---|
| LMArena Non-English | 1273 | 1261 |
| LMArena Chinese | 1318 | 1337 |
| LMArena Russian | 1289 | 1240 |
| LMArena French | 1289 | — |
| LMArena German | 1258 | — |
| LMArena Japanese | 1228 | — |
| LMArena Korean | 1209 | — |
| LMArena Spanish | 1248 | — |

## Instruction Following

- DeepSeek-V2.5 (Sep 2024): 67.5 (#194)
- Granite 4.1 8b: 66.9 (#203)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Granite 4.1 8b |
|---|---|---|
| LMArena Instruction Following | 1280 | 1269 |

## Long Context

- DeepSeek-V2.5 (Sep 2024): 39.5 (#174)
- Granite 4.1 8b: 38.7 (#193)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Granite 4.1 8b |
|---|---|---|
| LMArena Longer Query | 1301 | 1275 |

## Writing & Preference

- DeepSeek-V2.5 (Sep 2024): 49.8 (#187)
- Granite 4.1 8b: 48.1 (#204)

| Benchmark | DeepSeek-V2.5 (Sep 2024) | Granite 4.1 8b |
|---|---|---|
| LMArena Text | 1294 | 1290 |
| LMArena Creative Writing | 1285 | 1251 |
| LMArena Multi-Turn | 1297 | 1268 |

## FAQ

### Is DeepSeek-V2.5 (Sep 2024) better than Granite 4.1 8b?

DeepSeek-V2.5 (Sep 2024) and Granite 4.1 8b score almost the same on the Noometry Index (37.6 vs 37.4), so choose on price, context window or the category you care about most.

### Is DeepSeek-V2.5 (Sep 2024) or Granite 4.1 8b better for coding?

DeepSeek-V2.5 (Sep 2024) scores higher on coding benchmarks: 31.7 versus 30.1 in the Noometry coding category.

### How many benchmarks do DeepSeek-V2.5 (Sep 2024) and Granite 4.1 8b share?

12 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and Granite 4.1 8b has 13.