# Nemotron 3 Ultra vs Phi 3 Mini 128k Instruct

> Nemotron 3 Ultra is the stronger model overall, scoring 44.7 to 29.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/nemotron-3-ultra-vs-phi-3-mini-128k-instruct
- Last updated: 2026-10-10
- Shared benchmarks: 16

## Summary

- They share 16 benchmarks with published results for both. Nemotron 3 Ultra scores higher in 8 categories and Phi 3 Mini 128k Instruct in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Nemotron 3 Ultra leads 66.3 to 27.3.

## Snapshot

| | Nemotron 3 Ultra | Phi 3 Mini 128k Instruct |
|---|---|---|
| Provider | NVIDIA | Microsoft |
| Noometry Index | 44.7 | 29.1 |
| Rank | 71 | 303 |
| Context | 262K | — |
| Input $/M | $0.60 | — |
| Output $/M | $2.40 | — |
| Weights | Open | Open |

## Coding

- Nemotron 3 Ultra: 37.7 (#174)
- Phi 3 Mini 128k Instruct: 28.3 (#307)

| Benchmark | Nemotron 3 Ultra | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Coding | 1468 | 1040 |
| FrontierCode | 13.6% | — |
| SciCode | 40.3% | — |
| WeirdML | 43.5% | — |
| BigCodeBench Instruct | — | 29.6% |
| BigCodeBench Complete | — | 40.6% |

## Reasoning

- Nemotron 3 Ultra: 30.3 (#78)
- Phi 3 Mini 128k Instruct: 18.7 (#254)

| Benchmark | Nemotron 3 Ultra | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1452 | 1028 |
| 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)
- Phi 3 Mini 128k Instruct: 29.2 (#220)

| Benchmark | Nemotron 3 Ultra | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Math | 1456 | 1089 |
| OTIS Mock AIME 2024-2025 | 86.7% | — |
| ProofBench | 2% | — |

## Knowledge

- Nemotron 3 Ultra: 52.5 (#56)
- Phi 3 Mini 128k Instruct: 26.3 (#251)

| Benchmark | Nemotron 3 Ultra | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Expert | 1472 | 984 |
| GPQA Diamond | 85.4% | — |

## Multilingual

- Nemotron 3 Ultra: 53.7 (#61)
- Phi 3 Mini 128k Instruct: 25.4 (#280)

| Benchmark | Nemotron 3 Ultra | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Non-English | 1427 | 1000 |
| LMArena Chinese | 1498 | 1016 |
| LMArena French | 1475 | 1038 |
| LMArena German | 1471 | 1006 |
| LMArena Korean | 1387 | 856 |
| LMArena Russian | 1415 | 1004 |
| LMArena Spanish | 1452 | 1058 |
| LMArena Japanese | — | 899 |

## Instruction Following

- Nemotron 3 Ultra: 74.9 (#84)
- Phi 3 Mini 128k Instruct: 52.1 (#289)

| Benchmark | Nemotron 3 Ultra | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Instruction Following | 1417 | 1023 |

## Long Context

- Nemotron 3 Ultra: 43.9 (#77)
- Phi 3 Mini 128k Instruct: 30.3 (#284)

| Benchmark | Nemotron 3 Ultra | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Longer Query | 1437 | 996 |

## Writing & Preference

- Nemotron 3 Ultra: 66.3 (#35)
- Phi 3 Mini 128k Instruct: 27.3 (#296)

| Benchmark | Nemotron 3 Ultra | Phi 3 Mini 128k Instruct |
|---|---|---|
| LMArena Text | 1444 | 1050 |
| LMArena Creative Writing | 1392 | 1024 |
| LMArena Multi-Turn | 1412 | 989 |
| EQ-Bench Creative Writing | 1692 | — |

## FAQ

### Is Nemotron 3 Ultra better than Phi 3 Mini 128k Instruct?

Nemotron 3 Ultra is the stronger model overall, scoring 44.7 to 29.1 on the Noometry Index.

### Is Nemotron 3 Ultra or Phi 3 Mini 128k Instruct better for coding?

Nemotron 3 Ultra scores higher on coding benchmarks: 37.7 versus 28.3 in the Noometry coding category.

### How many benchmarks do Nemotron 3 Ultra and Phi 3 Mini 128k Instruct share?

16 benchmarks have published results for both models. Nemotron 3 Ultra has 29 scored results on Noometry and Phi 3 Mini 128k Instruct has 19.