Model comparison
Grok-3 mini vs Nemotron 3 Super
Grok-3 mini is the stronger model overall, scoring 41.2 to 40.1 on the Noometry Index.
Last verified . 16 shared benchmarks.
NVIDIASummary
- They share 16 benchmarks with published results for both. Grok-3 mini scores higher in 4 categories and Nemotron 3 Super in 4 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Grok-3 mini leads 46.4 to 38.9.
- Nemotron 3 Super has downloadable open weights; the other is API-only.
Side by side
| Grok-3 mini | Nemotron 3 Super | |
|---|---|---|
| Provider | xAI | NVIDIA |
| Noometry Index | 41.2 | 40.1 |
| Released | 2025-04-09 | 2026-03-11 |
| Weights | Proprietary | Open |
| Context window | — | 262K |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.08 |
| Output $ / M tokens | — | $0.45 |
| Results tracked | 35 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok-3 mini leads
Grok-3 mini: 40.8 (#131), Nemotron 3 Super: 39.4 (#158)
| Benchmark | Grok-3 mini | Nemotron 3 Super |
|---|---|---|
| WeirdML | 42.6% | 38% |
| LMArena Coding | 1379 | 1403 |
| Aider Polyglot | 49.3% | — |
| SciCode | — | 36% |
| ALE-Bench | — | 213.9 |
Reasoning Nemotron 3 Super leads
Grok-3 mini: 13.6 (#334), Nemotron 3 Super: 18.7 (#276)
| Benchmark | Grok-3 mini | Nemotron 3 Super |
|---|---|---|
| LMArena Hard Prompts | 1375 | 1386 |
| ARC-AGI-2 | 0.4% | — |
| Kagi LLM Benchmark | 61.3% | — |
| NYT Connections (extended) | — | 15.4% |
| ARC-AGI-1 | 16.5% | — |
| CritPt | — | 3.1% |
| Epoch Capabilities Index | 140.35 | — |
Math Grok-3 mini leads
Grok-3 mini: 42.1 (#85), Nemotron 3 Super: 39.6 (#101)
| Benchmark | Grok-3 mini | Nemotron 3 Super |
|---|---|---|
| LMArena Math | 1386 | 1380 |
| MathArena Final-Answer Competitions | — | 60.4% |
| OTIS Mock AIME 2024-2025 | 77.8% | — |
| Omni-MATH | 31.8% | — |
| MATH Level 5 | 90.9% | — |
| FrontierMath (Feb 2025 set) | 5.9% | — |
Knowledge Grok-3 mini leads
Grok-3 mini: 46.4 (#81), Nemotron 3 Super: 38.9 (#139)
| Benchmark | Grok-3 mini | Nemotron 3 Super |
|---|---|---|
| LMArena Expert | 1395 | 1398 |
| GPQA Diamond | 76.3% | — |
| MMLU-Pro | 79.9% | — |
| Confabulations | 10.8% | — |
| GPQA (HELM) | 67.5% | — |
Multilingual Too close to call
Grok-3 mini: 48.1 (#145), Nemotron 3 Super: 48.4 (#144)
| Benchmark | Grok-3 mini | Nemotron 3 Super |
|---|---|---|
| LMArena Non-English | 1352 | 1355 |
| LMArena Chinese | 1387 | 1432 |
| LMArena French | 1357 | 1405 |
| LMArena German | 1349 | 1341 |
| LMArena Russian | 1353 | 1336 |
| LMArena Spanish | 1381 | 1417 |
| LMArena Japanese | 1342 | — |
| LMArena Korean | 1335 | — |
Instruction Following Grok-3 mini leads
Grok-3 mini: 78.5 (#9), Nemotron 3 Super: 71.2 (#154)
| Benchmark | Grok-3 mini | Nemotron 3 Super |
|---|---|---|
| LMArena Instruction Following | 1357 | 1347 |
| IFEval | 95.1% | — |
Long Context Too close to call
Grok-3 mini: 41.0 (#147), Nemotron 3 Super: 41.5 (#139)
| Benchmark | Grok-3 mini | Nemotron 3 Super |
|---|---|---|
| LMArena Longer Query | 1372 | 1362 |
| Fiction.LiveBench | 66.7% | — |
Writing & Preference Nemotron 3 Super leads
Grok-3 mini: 52.5 (#169), Nemotron 3 Super: 55.9 (#140)
| Benchmark | Grok-3 mini | Nemotron 3 Super |
|---|---|---|
| LMArena Text | 1370 | 1378 |
| LMArena Creative Writing | 1342 | 1317 |
| LMArena Multi-Turn | 1355 | 1369 |
| Short-Story Creative Writing | 73.5% | — |
| WildBench | 65.1% | — |
Frequently asked questions
Is Grok-3 mini better than Nemotron 3 Super?
Grok-3 mini is the stronger model overall, scoring 41.2 to 40.1 on the Noometry Index.
Is Grok-3 mini or Nemotron 3 Super better for coding?
Grok-3 mini scores higher on coding benchmarks: 40.8 versus 39.4 in the Noometry coding category.
How many benchmarks do Grok-3 mini and Nemotron 3 Super share?
16 benchmarks have published results for both models. Grok-3 mini has 35 scored results on Noometry and Nemotron 3 Super has 21.