Model comparison
DeepSeek-V2.5 (Sep 2024) vs Granite 4.2 30b
Granite 4.2 30b is the stronger model overall, scoring 41.8 to 37.6 on the Noometry Index.
Last verified . 11 shared benchmarks.
DeepSeekSummary
- They share 11 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 0 categories and Granite 4.2 30b in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in coding, where Granite 4.2 30b leads 41.0 to 31.7.
Side by side
| DeepSeek-V2.5 (Sep 2024) | Granite 4.2 30b | |
|---|---|---|
| Provider | DeepSeek | IBM |
| Noometry Index | 37.6 | 41.8 |
| Released | 2024-09-06 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 22 | 11 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Granite 4.2 30b leads
DeepSeek-V2.5 (Sep 2024): 31.7 (#281), Granite 4.2 30b: 41.0 (#126)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Granite 4.2 30b |
|---|---|---|
| LMArena Coding | 1309 | 1396 |
| Aider Polyglot | 17.8% | — |
| BigCodeBench Instruct | 48.6% | — |
| BigCodeBench Complete | 53.2% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |
Reasoning Granite 4.2 30b leads
DeepSeek-V2.5 (Sep 2024): 25.6 (#145), Granite 4.2 30b: 27.8 (#112)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Granite 4.2 30b |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1374 |
Math Not comparable
DeepSeek-V2.5 (Sep 2024): 35.9 (#177), Granite 4.2 30b: —
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Granite 4.2 30b |
|---|---|---|
| LMArena Math | 1288 | — |
Knowledge Granite 4.2 30b leads
DeepSeek-V2.5 (Sep 2024): 34.8 (#193), Granite 4.2 30b: 39.1 (#138)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Granite 4.2 30b |
|---|---|---|
| LMArena Expert | 1266 | 1406 |
Multilingual Granite 4.2 30b leads
DeepSeek-V2.5 (Sep 2024): 42.5 (#193), Granite 4.2 30b: 47.3 (#151)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Granite 4.2 30b |
|---|---|---|
| LMArena Non-English | 1273 | 1340 |
| LMArena Chinese | 1318 | 1414 |
| LMArena Russian | 1289 | 1343 |
| LMArena French | 1289 | — |
| LMArena German | 1258 | — |
| LMArena Japanese | 1228 | — |
| LMArena Korean | 1209 | — |
| LMArena Spanish | 1248 | — |
Instruction Following Granite 4.2 30b leads
DeepSeek-V2.5 (Sep 2024): 67.5 (#194), Granite 4.2 30b: 71.2 (#155)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Granite 4.2 30b |
|---|---|---|
| LMArena Instruction Following | 1280 | 1347 |
Long Context Granite 4.2 30b leads
DeepSeek-V2.5 (Sep 2024): 39.5 (#174), Granite 4.2 30b: 41.4 (#140)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Granite 4.2 30b |
|---|---|---|
| LMArena Longer Query | 1301 | 1359 |
Writing & Preference Granite 4.2 30b leads
DeepSeek-V2.5 (Sep 2024): 49.8 (#187), Granite 4.2 30b: 53.8 (#156)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Granite 4.2 30b |
|---|---|---|
| LMArena Text | 1294 | 1361 |
| LMArena Creative Writing | 1285 | 1288 |
| LMArena Multi-Turn | 1297 | 1339 |
Frequently asked questions
Is DeepSeek-V2.5 (Sep 2024) better than Granite 4.2 30b?
Granite 4.2 30b is the stronger model overall, scoring 41.8 to 37.6 on the Noometry Index.
Is DeepSeek-V2.5 (Sep 2024) or Granite 4.2 30b better for coding?
Granite 4.2 30b scores higher on coding benchmarks: 41.0 versus 31.7 in the Noometry coding category.
How many benchmarks do DeepSeek-V2.5 (Sep 2024) and Granite 4.2 30b share?
11 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and Granite 4.2 30b has 11.