# Nemotron 3 Super vs Step 3.5 Flash

> Step 3.5 Flash is the stronger model overall, scoring 41.7 to 39.6 on the Noometry Index.

- Canonical page: https://noometry.com/compare/nemotron-3-super-vs-step-3-5-flash
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Nemotron 3 Super scores higher in 0 categories and Step 3.5 Flash in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Step 3.5 Flash leads 21.2 to 17.9.
- The biggest single-benchmark swing is NYT Connections (extended): 15.4% for Nemotron 3 Super and 28.4% for Step 3.5 Flash.
- Step 3.5 Flash is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.08 / $0.45 for Nemotron 3 Super.
- Nemotron 3 Super accepts more context: 262K tokens versus 256K.

## Snapshot

| | Nemotron 3 Super | Step 3.5 Flash |
|---|---|---|
| Provider | NVIDIA | StepFun |
| Noometry Index | 39.6 | 41.7 |
| Rank | 147 | 116 |
| Context | 262K | 256K |
| Input $/M | $0.08 | $0.10 |
| Output $/M | $0.45 | $0.30 |
| Weights | Open | Open |

## Coding

- Nemotron 3 Super: 38.9 (#153)
- Step 3.5 Flash: 41.7 (#106)

| Benchmark | Nemotron 3 Super | Step 3.5 Flash |
|---|---|---|
| LMArena Coding | 1403 | 1436 |
| SciCode | 36% | — |
| WeirdML | 38% | — |
| ALE-Bench | 213.9 | — |

## Reasoning

- Nemotron 3 Super: 17.9 (#274)
- Step 3.5 Flash: 21.2 (#202)

| Benchmark | Nemotron 3 Super | Step 3.5 Flash |
|---|---|---|
| NYT Connections (extended) | 15.4% | 28.4% |
| LMArena Hard Prompts | 1386 | 1411 |
| CritPt | 3.1% | — |

## Math

- Nemotron 3 Super: 37.6 (#95)
- Step 3.5 Flash: 40.6 (#77)

| Benchmark | Nemotron 3 Super | Step 3.5 Flash |
|---|---|---|
| MathArena Final-Answer Competitions | 60.4% | 66.8% |
| LMArena Math | 1381 | 1408 |

## Knowledge

- Nemotron 3 Super: 38.2 (#136)
- Step 3.5 Flash: 39.0 (#127)

| Benchmark | Nemotron 3 Super | Step 3.5 Flash |
|---|---|---|
| LMArena Expert | 1397 | 1422 |

## Multilingual

- Nemotron 3 Super: 48.6 (#139)
- Step 3.5 Flash: 50.7 (#115)

| Benchmark | Nemotron 3 Super | Step 3.5 Flash |
|---|---|---|
| LMArena Non-English | 1356 | 1386 |
| LMArena Chinese | 1430 | 1448 |
| LMArena French | 1404 | 1421 |
| LMArena German | 1341 | 1404 |
| LMArena Russian | 1336 | 1385 |
| LMArena Spanish | 1417 | 1419 |
| LMArena Japanese | — | 1353 |
| LMArena Korean | — | 1350 |

## Instruction Following

- Nemotron 3 Super: 71.4 (#149)
- Step 3.5 Flash: 73.3 (#119)

| Benchmark | Nemotron 3 Super | Step 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1347 | 1385 |

## Long Context

- Nemotron 3 Super: 41.5 (#134)
- Step 3.5 Flash: 42.8 (#112)

| Benchmark | Nemotron 3 Super | Step 3.5 Flash |
|---|---|---|
| LMArena Longer Query | 1362 | 1402 |

## Writing & Preference

- Nemotron 3 Super: 56.1 (#135)
- Step 3.5 Flash: 59.0 (#108)

| Benchmark | Nemotron 3 Super | Step 3.5 Flash |
|---|---|---|
| LMArena Text | 1378 | 1403 |
| LMArena Creative Writing | 1317 | 1357 |
| LMArena Multi-Turn | 1369 | 1405 |

## FAQ

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

Step 3.5 Flash is the stronger model overall, scoring 41.7 to 39.6 on the Noometry Index.

### Which is cheaper, Nemotron 3 Super 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 Super lists at $0.08 and $0.45.

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

Step 3.5 Flash scores higher on coding benchmarks: 41.7 versus 38.9 in the Noometry coding category.

### Which has the bigger context window?

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

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

17 benchmarks have published results for both models. Nemotron 3 Super has 21 scored results on Noometry and Step 3.5 Flash has 19.