# Hy4 preview vs Nemotron 3 Ultra

> Hy4 preview is the stronger model overall, scoring 45.3 to 42.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/hy4-preview-vs-nemotron-3-ultra
- Last updated: 2026-10-12
- Shared benchmarks: 1

## Summary

- They share 1 benchmark with published results for both. Hy4 preview scores higher in 3 categories and Nemotron 3 Ultra in 0 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in math, where Hy4 preview leads 55.7 to 35.3.
- The biggest single-benchmark swing is ProofBench: 75% for Hy4 preview and 2% for Nemotron 3 Ultra.
- Nemotron 3 Ultra is cheaper at $0.60 / $2.40 per million input/output tokens, against $0.83 / $2.50 for Hy4 preview.
- Hy4 preview accepts more context: 1.05M tokens versus 262K.

## Snapshot

| | Hy4 preview | Nemotron 3 Ultra |
|---|---|---|
| Provider | Tencent | NVIDIA |
| Noometry Index | 45.3 | 42.5 |
| Rank | 73 | 113 |
| Context | 1.05M | 262K |
| Input $/M | $0.83 | $0.60 |
| Output $/M | $2.50 | $2.40 |
| Weights | Open | Open |

## Coding

- Hy4 preview: 51.6 (#38)
- Nemotron 3 Ultra: 38.1 (#182)

| Benchmark | Hy4 preview | Nemotron 3 Ultra |
|---|---|---|
| FrontierCode | — | 13.6% |
| LMArena WebDev | 1632 | — |
| SciCode | — | 40.3% |
| WeirdML | — | 43.5% |
| LMArena Coding | — | 1468 |

## Agentic & Tool Use

- Hy4 preview: —
- Nemotron 3 Ultra: 23.4 (#126)

| Benchmark | Hy4 preview | Nemotron 3 Ultra |
|---|---|---|
| APEX-Agents | — | 22.7% |

## Reasoning

- Hy4 preview: 31.9 (#79)
- Nemotron 3 Ultra: 31.0 (#82)

| Benchmark | Hy4 preview | Nemotron 3 Ultra |
|---|---|---|
| NYT Connections (extended) | 68.2% | — |
| CritPt | — | 3.1% |
| Chess Puzzles | — | 12% |
| LMArena Hard Prompts | — | 1452 |
| Mystery Game Puzzles | — | 20% |
| DTBench | — | 90.1% |
| LMCA | — | 36.9% |
| Epoch Capabilities Index | — | 146.17 |

## Math

- Hy4 preview: 55.7 (#42)
- Nemotron 3 Ultra: 35.3 (#187)

| Benchmark | Hy4 preview | Nemotron 3 Ultra |
|---|---|---|
| ProofBench | 75% | 2% |
| OTIS Mock AIME 2024-2025 | — | 86.7% |
| LMArena Math | — | 1457 |

## Knowledge

- Hy4 preview: —
- Nemotron 3 Ultra: 52.5 (#61)

| Benchmark | Hy4 preview | Nemotron 3 Ultra |
|---|---|---|
| GPQA Diamond | — | 85.4% |
| LMArena Expert | — | 1472 |

## Multilingual

- Hy4 preview: —
- Nemotron 3 Ultra: 53.5 (#64)

| Benchmark | Hy4 preview | Nemotron 3 Ultra |
|---|---|---|
| LMArena Non-English | — | 1427 |
| LMArena Chinese | — | 1497 |
| LMArena French | — | 1472 |
| LMArena German | — | 1471 |
| LMArena Korean | — | 1386 |
| LMArena Russian | — | 1417 |
| LMArena Spanish | — | 1454 |

## Instruction Following

- Hy4 preview: —
- Nemotron 3 Ultra: 74.7 (#88)

| Benchmark | Hy4 preview | Nemotron 3 Ultra |
|---|---|---|
| LMArena Instruction Following | — | 1418 |

## Long Context

- Hy4 preview: —
- Nemotron 3 Ultra: 43.9 (#81)

| Benchmark | Hy4 preview | Nemotron 3 Ultra |
|---|---|---|
| LMArena Longer Query | — | 1437 |

## Writing & Preference

- Hy4 preview: —
- Nemotron 3 Ultra: 66.3 (#36)

| Benchmark | Hy4 preview | Nemotron 3 Ultra |
|---|---|---|
| LMArena Text | — | 1445 |
| LMArena Creative Writing | — | 1398 |
| EQ-Bench Creative Writing | — | 1692 |
| LMArena Multi-Turn | — | 1411 |

## FAQ

### Is Hy4 preview better than Nemotron 3 Ultra?

Hy4 preview is the stronger model overall, scoring 45.3 to 42.5 on the Noometry Index.

### Which is cheaper, Hy4 preview or Nemotron 3 Ultra?

Nemotron 3 Ultra is cheaper. It lists at $0.60 per million input tokens and $2.40 per million output tokens; Hy4 preview lists at $0.83 and $2.50.

### Is Hy4 preview or Nemotron 3 Ultra better for coding?

Hy4 preview scores higher on coding benchmarks: 51.6 versus 38.1 in the Noometry coding category.

### Which has the bigger context window?

Hy4 preview does, with 1.05M tokens against 262K.

### How many benchmarks do Hy4 preview and Nemotron 3 Ultra share?

1 benchmark has published results for both models. Hy4 preview has 3 scored results on Noometry and Nemotron 3 Ultra has 30.