# Nemotron 3 Ultra vs Step 3.5 Flash

> Nemotron 3 Ultra and Step 3.5 Flash score almost the same on the Noometry Index (42.5 vs 42.3), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/nemotron-3-ultra-vs-step-3-5-flash
- Last updated: 2026-10-12
- Shared benchmarks: 16

## Summary

- They share 16 benchmarks with published results for both. Nemotron 3 Ultra scores higher in 6 categories and Step 3.5 Flash in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Nemotron 3 Ultra leads 52.5 to 39.6.
- Step 3.5 Flash is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.60 / $2.40 for Nemotron 3 Ultra.
- Nemotron 3 Ultra accepts more context: 262K tokens versus 256K.

## Snapshot

| | Nemotron 3 Ultra | Step 3.5 Flash |
|---|---|---|
| Provider | NVIDIA | StepFun |
| Noometry Index | 42.5 | 42.3 |
| Rank | 113 | 116 |
| Context | 262K | 256K |
| Input $/M | $0.60 | $0.10 |
| Output $/M | $2.40 | $0.30 |
| Weights | Open | Open |

## Coding

- Nemotron 3 Ultra: 38.1 (#182)
- Step 3.5 Flash: 42.4 (#105)

| Benchmark | Nemotron 3 Ultra | Step 3.5 Flash |
|---|---|---|
| LMArena Coding | 1468 | 1436 |
| FrontierCode | 13.6% | — |
| SciCode | 40.3% | — |
| WeirdML | 43.5% | — |

## Agentic & Tool Use

- Nemotron 3 Ultra: 23.4 (#126)
- Step 3.5 Flash: —

| Benchmark | Nemotron 3 Ultra | Step 3.5 Flash |
|---|---|---|
| APEX-Agents | 22.7% | — |

## Reasoning

- Nemotron 3 Ultra: 31.0 (#82)
- Step 3.5 Flash: 22.2 (#202)

| Benchmark | Nemotron 3 Ultra | Step 3.5 Flash |
|---|---|---|
| LMArena Hard Prompts | 1452 | 1411 |
| NYT Connections (extended) | — | 28.4% |
| CritPt | 3.1% | — |
| Chess Puzzles | 12% | — |
| Mystery Game Puzzles | 20% | — |
| DTBench | 90.1% | — |
| LMCA | 36.9% | — |
| Epoch Capabilities Index | 146.17 | — |

## Math

- Nemotron 3 Ultra: 35.3 (#187)
- Step 3.5 Flash: 42.6 (#84)

| Benchmark | Nemotron 3 Ultra | Step 3.5 Flash |
|---|---|---|
| LMArena Math | 1457 | 1408 |
| MathArena Final-Answer Competitions | — | 66.8% |
| OTIS Mock AIME 2024-2025 | 86.7% | — |
| ProofBench | 2% | — |

## Knowledge

- Nemotron 3 Ultra: 52.5 (#61)
- Step 3.5 Flash: 39.6 (#132)

| Benchmark | Nemotron 3 Ultra | Step 3.5 Flash |
|---|---|---|
| LMArena Expert | 1472 | 1421 |
| GPQA Diamond | 85.4% | — |

## Multilingual

- Nemotron 3 Ultra: 53.5 (#64)
- Step 3.5 Flash: 50.5 (#119)

| Benchmark | Nemotron 3 Ultra | Step 3.5 Flash |
|---|---|---|
| LMArena Non-English | 1427 | 1385 |
| LMArena Chinese | 1497 | 1447 |
| LMArena French | 1472 | 1421 |
| LMArena German | 1471 | 1405 |
| LMArena Korean | 1386 | 1352 |
| LMArena Russian | 1417 | 1385 |
| LMArena Spanish | 1454 | 1419 |
| LMArena Japanese | — | 1354 |

## Instruction Following

- Nemotron 3 Ultra: 74.7 (#88)
- Step 3.5 Flash: 73.1 (#124)

| Benchmark | Nemotron 3 Ultra | Step 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1418 | 1385 |

## Long Context

- Nemotron 3 Ultra: 43.9 (#81)
- Step 3.5 Flash: 42.8 (#117)

| Benchmark | Nemotron 3 Ultra | Step 3.5 Flash |
|---|---|---|
| LMArena Longer Query | 1437 | 1402 |

## Writing & Preference

- Nemotron 3 Ultra: 66.3 (#36)
- Step 3.5 Flash: 58.8 (#113)

| Benchmark | Nemotron 3 Ultra | Step 3.5 Flash |
|---|---|---|
| LMArena Text | 1445 | 1403 |
| LMArena Creative Writing | 1398 | 1357 |
| LMArena Multi-Turn | 1411 | 1405 |
| EQ-Bench Creative Writing | 1692 | — |

## FAQ

### Is Nemotron 3 Ultra better than Step 3.5 Flash?

Nemotron 3 Ultra and Step 3.5 Flash score almost the same on the Noometry Index (42.5 vs 42.3), so choose on price, context window or the category you care about most.

### Which is cheaper, Nemotron 3 Ultra or Step 3.5 Flash?

Step 3.5 Flash is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; Nemotron 3 Ultra lists at $0.60 and $2.40.

### Is Nemotron 3 Ultra or Step 3.5 Flash better for coding?

Step 3.5 Flash scores higher on coding benchmarks: 42.4 versus 38.1 in the Noometry coding category.

### Which has the bigger context window?

Nemotron 3 Ultra does, with 262K tokens against 256K.

### How many benchmarks do Nemotron 3 Ultra and Step 3.5 Flash share?

16 benchmarks have published results for both models. Nemotron 3 Ultra has 30 scored results on Noometry and Step 3.5 Flash has 19.