Model comparison
Granite 4.2 30b vs Nemotron 3 Super
Granite 4.2 30b is the stronger model overall, scoring 41.4 to 39.6 on the Noometry Index.
Last verified . 11 shared benchmarks.
NVIDIASummary
- They share 11 benchmarks with published results for both. Granite 4.2 30b scores higher in 3 categories and Nemotron 3 Super in 4 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Granite 4.2 30b leads 26.7 to 17.9.
Side by side
| Granite 4.2 30b | Nemotron 3 Super | |
|---|---|---|
| Provider | IBM | NVIDIA |
| Noometry Index | 41.4 | 39.6 |
| Released | — | 2026-03-11 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.08 |
| Output $ / M tokens | — | $0.45 |
| Results tracked | 11 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Granite 4.2 30b leads
Granite 4.2 30b: 40.4 (#127), Nemotron 3 Super: 38.9 (#153)
| Benchmark | Granite 4.2 30b | Nemotron 3 Super |
|---|---|---|
| LMArena Coding | 1394 | 1403 |
| SciCode | — | 36% |
| WeirdML | — | 38% |
| ALE-Bench | — | 213.9 |
Reasoning Granite 4.2 30b leads
Granite 4.2 30b: 26.7 (#114), Nemotron 3 Super: 17.9 (#274)
| Benchmark | Granite 4.2 30b | Nemotron 3 Super |
|---|---|---|
| LMArena Hard Prompts | 1375 | 1386 |
| NYT Connections (extended) | — | 15.4% |
| CritPt | — | 3.1% |
Math Not comparable
Granite 4.2 30b: —, Nemotron 3 Super: 37.6 (#95)
| Benchmark | Granite 4.2 30b | Nemotron 3 Super |
|---|---|---|
| MathArena Final-Answer Competitions | — | 60.4% |
| LMArena Math | — | 1381 |
Knowledge Too close to call
Granite 4.2 30b: 38.5 (#134), Nemotron 3 Super: 38.2 (#136)
| Benchmark | Granite 4.2 30b | Nemotron 3 Super |
|---|---|---|
| LMArena Expert | 1405 | 1397 |
Multilingual Nemotron 3 Super leads
Granite 4.2 30b: 47.4 (#146), Nemotron 3 Super: 48.6 (#139)
| Benchmark | Granite 4.2 30b | Nemotron 3 Super |
|---|---|---|
| LMArena Non-English | 1340 | 1356 |
| LMArena Chinese | 1415 | 1430 |
| LMArena Russian | 1342 | 1336 |
| LMArena French | — | 1404 |
| LMArena German | — | 1341 |
| LMArena Spanish | — | 1417 |
Instruction Following Too close to call
Granite 4.2 30b: 71.3 (#150), Nemotron 3 Super: 71.4 (#149)
| Benchmark | Granite 4.2 30b | Nemotron 3 Super |
|---|---|---|
| LMArena Instruction Following | 1346 | 1347 |
Long Context Too close to call
Granite 4.2 30b: 41.4 (#135), Nemotron 3 Super: 41.5 (#134)
| Benchmark | Granite 4.2 30b | Nemotron 3 Super |
|---|---|---|
| LMArena Longer Query | 1359 | 1362 |
Writing & Preference Nemotron 3 Super leads
Granite 4.2 30b: 54.3 (#147), Nemotron 3 Super: 56.1 (#135)
| Benchmark | Granite 4.2 30b | Nemotron 3 Super |
|---|---|---|
| LMArena Text | 1363 | 1378 |
| LMArena Creative Writing | 1294 | 1317 |
| LMArena Multi-Turn | 1340 | 1369 |
Frequently asked questions
Is Granite 4.2 30b better than Nemotron 3 Super?
Granite 4.2 30b is the stronger model overall, scoring 41.4 to 39.6 on the Noometry Index.
Is Granite 4.2 30b or Nemotron 3 Super better for coding?
Granite 4.2 30b scores higher on coding benchmarks: 40.4 versus 38.9 in the Noometry coding category.
How many benchmarks do Granite 4.2 30b and Nemotron 3 Super share?
11 benchmarks have published results for both models. Granite 4.2 30b has 11 scored results on Noometry and Nemotron 3 Super has 21.