Model comparison
DeepSeek LLM 67B vs Granite 4.2 30b
Granite 4.2 30b is the stronger model overall, scoring 41.4 to 24.8 on the Noometry Index.
Last verified . 9 shared benchmarks.
DeepSeekSummary
- They share 9 benchmarks with published results for both. DeepSeek LLM 67B 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 knowledge, where Granite 4.2 30b leads 38.5 to 7.1.
Side by side
| DeepSeek LLM 67B | Granite 4.2 30b | |
|---|---|---|
| Provider | DeepSeek | IBM |
| Noometry Index | 24.8 | 41.4 |
| Released | 2023-11-29 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 15 | 11 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Granite 4.2 30b leads
DeepSeek LLM 67B: 31.3 (#273), Granite 4.2 30b: 40.4 (#127)
| Benchmark | DeepSeek LLM 67B | Granite 4.2 30b |
|---|---|---|
| LMArena Coding | 1096 | 1394 |
Reasoning Granite 4.2 30b leads
DeepSeek LLM 67B: 15.9 (#300), Granite 4.2 30b: 26.7 (#114)
| Benchmark | DeepSeek LLM 67B | Granite 4.2 30b |
|---|---|---|
| LMArena Hard Prompts | 1070 | 1375 |
| Chess Puzzles | 0% | — |
| Epoch Capabilities Index | 110.54 | — |
Math Not comparable
DeepSeek LLM 67B: 8.1 (#318), Granite 4.2 30b: —
| Benchmark | DeepSeek LLM 67B | Granite 4.2 30b |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.8% | — |
| LMArena Math | 1108 | — |
| MATH Level 5 | 6.4% | — |
Knowledge Granite 4.2 30b leads
DeepSeek LLM 67B: 7.1 (#308), Granite 4.2 30b: 38.5 (#134)
| Benchmark | DeepSeek LLM 67B | Granite 4.2 30b |
|---|---|---|
| GPQA Diamond | 24.6% | — |
| LMArena Expert | — | 1405 |
Multilingual Granite 4.2 30b leads
DeepSeek LLM 67B: 29.5 (#262), Granite 4.2 30b: 47.4 (#146)
| Benchmark | DeepSeek LLM 67B | Granite 4.2 30b |
|---|---|---|
| LMArena Non-English | 1073 | 1340 |
| LMArena Chinese | 1132 | 1415 |
| LMArena Russian | — | 1342 |
Instruction Following Granite 4.2 30b leads
DeepSeek LLM 67B: 55.7 (#272), Granite 4.2 30b: 71.3 (#150)
| Benchmark | DeepSeek LLM 67B | Granite 4.2 30b |
|---|---|---|
| LMArena Instruction Following | 1079 | 1346 |
Long Context Granite 4.2 30b leads
DeepSeek LLM 67B: 33.1 (#260), Granite 4.2 30b: 41.4 (#135)
| Benchmark | DeepSeek LLM 67B | Granite 4.2 30b |
|---|---|---|
| LMArena Longer Query | 1092 | 1359 |
Writing & Preference Granite 4.2 30b leads
DeepSeek LLM 67B: 31.8 (#277), Granite 4.2 30b: 54.3 (#147)
| Benchmark | DeepSeek LLM 67B | Granite 4.2 30b |
|---|---|---|
| LMArena Text | 1105 | 1363 |
| LMArena Creative Writing | 1067 | 1294 |
| LMArena Multi-Turn | 1082 | 1340 |
Frequently asked questions
Is DeepSeek LLM 67B better than Granite 4.2 30b?
Granite 4.2 30b is the stronger model overall, scoring 41.4 to 24.8 on the Noometry Index.
Is DeepSeek LLM 67B or Granite 4.2 30b better for coding?
Granite 4.2 30b scores higher on coding benchmarks: 40.4 versus 31.3 in the Noometry coding category.
How many benchmarks do DeepSeek LLM 67B and Granite 4.2 30b share?
9 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Granite 4.2 30b has 11.