Model comparison
Muse Spark vs Nemotron 3 Ultra
Muse Spark is the stronger model overall, scoring 50.6 to 42.5 on the Noometry Index.
Last verified . 22 shared benchmarks.
Meta
NVIDIASummary
- They share 22 benchmarks with published results for both. Muse Spark scores higher in 7 categories and Nemotron 3 Ultra in 1 category; 6 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Muse Spark leads 65.7 to 52.5.
- The biggest single-benchmark swing is ProofBench: 17% for Muse Spark and 2% for Nemotron 3 Ultra.
- Nemotron 3 Ultra has downloadable open weights; the other is API-only.
Side by side
| Muse Spark | Nemotron 3 Ultra | |
|---|---|---|
| Provider | Meta | NVIDIA |
| Noometry Index | 50.6 | 42.5 |
| Released | 2026-04-08 | 2026-06-04 |
| Weights | Proprietary | Open |
| Context window | — | 262K |
| Max output | — | 128K |
| Input $ / M tokens | — | $0.50 |
| Output $ / M tokens | — | $2.20 |
| Results tracked | 27 | 30 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Muse Spark leads
Muse Spark: 46.2 (#69), Nemotron 3 Ultra: 38.1 (#182)
| Benchmark | Muse Spark | Nemotron 3 Ultra |
|---|---|---|
| SciCode | 51.5% | 40.3% |
| LMArena Coding | 1481 | 1468 |
| FrontierCode | — | 13.6% |
| WeirdML | — | 43.5% |
Agentic & Tool Use Not comparable
Muse Spark: —, Nemotron 3 Ultra: 23.4 (#126)
| Benchmark | Muse Spark | Nemotron 3 Ultra |
|---|---|---|
| APEX-Agents | — | 22.7% |
Reasoning Muse Spark leads
Muse Spark: 35.9 (#67), Nemotron 3 Ultra: 31.0 (#82)
| Benchmark | Muse Spark | Nemotron 3 Ultra |
|---|---|---|
| CritPt | 11.3% | 3.1% |
| LMArena Hard Prompts | 1474 | 1452 |
| Epoch Capabilities Index | 152.04 | 146.17 |
| Chess Puzzles | — | 12% |
| Mystery Game Puzzles | — | 20% |
| DTBench | — | 90.1% |
| LMCA | — | 36.9% |
Math Muse Spark leads
Muse Spark: 47.8 (#66), Nemotron 3 Ultra: 35.3 (#187)
| Benchmark | Muse Spark | Nemotron 3 Ultra |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 88.9% | 86.7% |
| ProofBench | 17% | 2% |
| LMArena Math | 1455 | 1457 |
| FrontierMath (Feb 2025 set) | 39% | — |
| FrontierMath Tier 4 (v1) | 14.6% | — |
Knowledge Muse Spark leads
Muse Spark: 65.7 (#13), Nemotron 3 Ultra: 52.5 (#61)
| Benchmark | Muse Spark | Nemotron 3 Ultra |
|---|---|---|
| GPQA Diamond | 89.8% | 85.4% |
| LMArena Expert | 1457 | 1472 |
| Humanity's Last Exam | 40.6% | — |
Multimodal Not comparable
Muse Spark: 43.4 (#24), Nemotron 3 Ultra: —
| Benchmark | Muse Spark | Nemotron 3 Ultra |
|---|---|---|
| LMArena Vision | 1306 | — |
| LMArena Document | 1444 | — |
Multilingual Muse Spark leads
Muse Spark: 56.1 (#24), Nemotron 3 Ultra: 53.5 (#64)
| Benchmark | Muse Spark | Nemotron 3 Ultra |
|---|---|---|
| LMArena Non-English | 1464 | 1427 |
| LMArena Chinese | 1509 | 1497 |
| LMArena French | 1497 | 1472 |
| LMArena German | 1497 | 1471 |
| LMArena Korean | 1459 | 1386 |
| LMArena Russian | 1466 | 1417 |
| LMArena Spanish | 1472 | 1454 |
Instruction Following Muse Spark leads
Muse Spark: 75.9 (#51), Nemotron 3 Ultra: 74.7 (#88)
| Benchmark | Muse Spark | Nemotron 3 Ultra |
|---|---|---|
| LMArena Instruction Following | 1442 | 1418 |
Long Context Too close to call
Muse Spark: 44.4 (#69), Nemotron 3 Ultra: 43.9 (#81)
| Benchmark | Muse Spark | Nemotron 3 Ultra |
|---|---|---|
| LMArena Longer Query | 1451 | 1437 |
Writing & Preference Too close to call
Muse Spark: 66.0 (#39), Nemotron 3 Ultra: 66.3 (#36)
| Benchmark | Muse Spark | Nemotron 3 Ultra |
|---|---|---|
| LMArena Text | 1474 | 1445 |
| LMArena Creative Writing | 1459 | 1398 |
| LMArena Multi-Turn | 1477 | 1411 |
| EQ-Bench Creative Writing | — | 1692 |
Frequently asked questions
Is Muse Spark better than Nemotron 3 Ultra?
Muse Spark is the stronger model overall, scoring 50.6 to 42.5 on the Noometry Index.
Is Muse Spark or Nemotron 3 Ultra better for coding?
Muse Spark scores higher on coding benchmarks: 46.2 versus 38.1 in the Noometry coding category.
How many benchmarks do Muse Spark and Nemotron 3 Ultra share?
22 benchmarks have published results for both models. Muse Spark has 27 scored results on Noometry and Nemotron 3 Ultra has 30.