# Nemotron 3 Ultra vs Step 3

> Nemotron 3 Ultra is the stronger model overall, scoring 44.7 to 39.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/nemotron-3-ultra-vs-step-3
- Last updated: 2026-10-10
- Shared benchmarks: 15

## Summary

- They share 15 benchmarks with published results for both. Nemotron 3 Ultra scores higher in 6 categories and Step 3 in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Nemotron 3 Ultra leads 52.5 to 36.2.

## Snapshot

| | Nemotron 3 Ultra | Step 3 |
|---|---|---|
| Provider | NVIDIA | StepFun |
| Noometry Index | 44.7 | 39.9 |
| Rank | 71 | 145 |
| Context | 262K | — |
| Input $/M | $0.60 | — |
| Output $/M | $2.40 | — |
| Weights | Open | Open |

## Coding

- Nemotron 3 Ultra: 37.7 (#174)
- Step 3: 39.5 (#144)

| Benchmark | Nemotron 3 Ultra | Step 3 |
|---|---|---|
| LMArena Coding | 1468 | 1367 |
| FrontierCode | 13.6% | — |
| SciCode | 40.3% | — |
| WeirdML | 43.5% | — |

## Reasoning

- Nemotron 3 Ultra: 30.3 (#78)
- Step 3: 27.6 (#102)

| Benchmark | Nemotron 3 Ultra | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1452 | 1355 |
| Kagi LLM Benchmark | — | 62.3% |
| CritPt | 3.1% | — |
| Chess Puzzles | 12% | — |
| Mystery Game Puzzles | 20% | — |
| DTBench | 90.1% | — |
| LMCA | 36.9% | — |
| Epoch Capabilities Index | 146.2 | — |

## Math

- Nemotron 3 Ultra: 34.4 (#160)
- Step 3: 34.9 (#148)

| Benchmark | Nemotron 3 Ultra | Step 3 |
|---|---|---|
| LMArena Math | 1456 | 1366 |
| OTIS Mock AIME 2024-2025 | 86.7% | — |
| ProofBench | 2% | — |

## Knowledge

- Nemotron 3 Ultra: 52.5 (#56)
- Step 3: 36.2 (#161)

| Benchmark | Nemotron 3 Ultra | Step 3 |
|---|---|---|
| LMArena Expert | 1472 | 1333 |
| GPQA Diamond | 85.4% | — |

## Multimodal

- Nemotron 3 Ultra: —
- Step 3: 34.9 (#81)

| Benchmark | Nemotron 3 Ultra | Step 3 |
|---|---|---|
| LMArena Vision | — | 1176 |

## Multilingual

- Nemotron 3 Ultra: 53.7 (#61)
- Step 3: 46.5 (#154)

| Benchmark | Nemotron 3 Ultra | Step 3 |
|---|---|---|
| LMArena Non-English | 1427 | 1327 |
| LMArena Chinese | 1498 | 1396 |
| LMArena German | 1471 | 1371 |
| LMArena Korean | 1387 | 1271 |
| LMArena Russian | 1415 | 1331 |
| LMArena Spanish | 1452 | 1372 |
| LMArena French | 1475 | — |

## Instruction Following

- Nemotron 3 Ultra: 74.9 (#84)
- Step 3: 70.6 (#159)

| Benchmark | Nemotron 3 Ultra | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1417 | 1332 |

## Long Context

- Nemotron 3 Ultra: 43.9 (#77)
- Step 3: 40.3 (#152)

| Benchmark | Nemotron 3 Ultra | Step 3 |
|---|---|---|
| LMArena Longer Query | 1437 | 1326 |

## Writing & Preference

- Nemotron 3 Ultra: 66.3 (#35)
- Step 3: 54.5 (#146)

| Benchmark | Nemotron 3 Ultra | Step 3 |
|---|---|---|
| LMArena Text | 1444 | 1351 |
| LMArena Creative Writing | 1392 | 1322 |
| LMArena Multi-Turn | 1412 | 1340 |
| EQ-Bench Creative Writing | 1692 | — |

## FAQ

### Is Nemotron 3 Ultra better than Step 3?

Nemotron 3 Ultra is the stronger model overall, scoring 44.7 to 39.9 on the Noometry Index.

### Is Nemotron 3 Ultra or Step 3 better for coding?

Step 3 scores higher on coding benchmarks: 39.5 versus 37.7 in the Noometry coding category.

### How many benchmarks do Nemotron 3 Ultra and Step 3 share?

15 benchmarks have published results for both models. Nemotron 3 Ultra has 29 scored results on Noometry and Step 3 has 17.