Model comparison
Nemotron 3 Ultra vs Phi 3 Small 8k Instruct
Nemotron 3 Ultra is the stronger model overall, scoring 44.7 to 28.8 on the Noometry Index.
Last verified . 16 shared benchmarks.
NVIDIA
MicrosoftSummary
- They share 16 benchmarks with published results for both. Nemotron 3 Ultra scores higher in 8 categories and Phi 3 Small 8k 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 31.3.
Side by side
| Nemotron 3 Ultra | Phi 3 Small 8k Instruct | |
|---|---|---|
| Provider | NVIDIA | Microsoft |
| Noometry Index | 44.7 | 28.8 |
| Released | 2026-06-04 | 2024-04-23 |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.60 | — |
| Output $ / M tokens | $2.40 | — |
| Results tracked | 29 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nemotron 3 Ultra leads
Nemotron 3 Ultra: 37.7 (#174), Phi 3 Small 8k Instruct: 27.4 (#313)
| Benchmark | Nemotron 3 Ultra | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Coding | 1468 | 1102 |
| FrontierCode | 13.6% | — |
| SciCode | 40.3% | — |
| WeirdML | 43.5% | — |
| LiveBench Coding | — | 20.3% |
Reasoning Nemotron 3 Ultra leads
Nemotron 3 Ultra: 30.3 (#78), Phi 3 Small 8k Instruct: 14.2 (#319)
| Benchmark | Nemotron 3 Ultra | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1452 | 1100 |
| CritPt | 3.1% | — |
| Chess Puzzles | 12% | — |
| LiveBench Reasoning | — | 15.9% |
| Mystery Game Puzzles | 20% | — |
| DTBench | 90.1% | — |
| LiveBench Data Analysis | — | 30.3% |
| LMCA | 36.9% | — |
| Adversarial NLI | — | 58.1% |
| BIG-Bench Hard | — | 79.1% |
| Epoch Capabilities Index | 146.2 | — |
| HellaSwag | — | 77% |
| LiveBench | — | 24% |
| WinoGrande | — | 81.5% |
Math Nemotron 3 Ultra leads
Nemotron 3 Ultra: 34.4 (#160), Phi 3 Small 8k Instruct: 25.4 (#247)
| Benchmark | Nemotron 3 Ultra | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Math | 1456 | 1151 |
| OTIS Mock AIME 2024-2025 | 86.7% | — |
| ProofBench | 2% | — |
| LiveBench Math | — | 17.6% |
Knowledge Nemotron 3 Ultra leads
Nemotron 3 Ultra: 52.5 (#56), Phi 3 Small 8k Instruct: 28.5 (#237)
| Benchmark | Nemotron 3 Ultra | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Expert | 1472 | 1067 |
| GPQA Diamond | 85.4% | — |
| ARC (AI2) Challenge | — | 90.7% |
| MMLU | — | 75.7% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 58.1% |
Multilingual Nemotron 3 Ultra leads
Nemotron 3 Ultra: 53.7 (#61), Phi 3 Small 8k Instruct: 28.6 (#267)
| Benchmark | Nemotron 3 Ultra | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Non-English | 1427 | 1058 |
| LMArena Chinese | 1498 | 1061 |
| LMArena French | 1475 | 1134 |
| LMArena German | 1471 | 1080 |
| LMArena Korean | 1387 | 894 |
| LMArena Russian | 1415 | 1111 |
| LMArena Spanish | 1452 | 1111 |
| LMArena Japanese | — | 966 |
Instruction Following Nemotron 3 Ultra leads
Nemotron 3 Ultra: 74.9 (#84), Phi 3 Small 8k Instruct: 52.2 (#287)
| Benchmark | Nemotron 3 Ultra | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Instruction Following | 1417 | 1087 |
| LiveBench Instruction Following | — | 47.2% |
Long Context Nemotron 3 Ultra leads
Nemotron 3 Ultra: 43.9 (#77), Phi 3 Small 8k Instruct: 33.0 (#262)
| Benchmark | Nemotron 3 Ultra | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Longer Query | 1437 | 1088 |
Writing & Preference Nemotron 3 Ultra leads
Nemotron 3 Ultra: 66.3 (#35), Phi 3 Small 8k Instruct: 31.3 (#279)
| Benchmark | Nemotron 3 Ultra | Phi 3 Small 8k Instruct |
|---|---|---|
| LMArena Text | 1444 | 1110 |
| LMArena Creative Writing | 1392 | 1083 |
| LMArena Multi-Turn | 1412 | 1068 |
| EQ-Bench Creative Writing | 1692 | — |
| LiveBench Language | — | 12.9% |
Frequently asked questions
Is Nemotron 3 Ultra better than Phi 3 Small 8k Instruct?
Nemotron 3 Ultra is the stronger model overall, scoring 44.7 to 28.8 on the Noometry Index.
Is Nemotron 3 Ultra or Phi 3 Small 8k Instruct better for coding?
Nemotron 3 Ultra scores higher on coding benchmarks: 37.7 versus 27.4 in the Noometry coding category.
How many benchmarks do Nemotron 3 Ultra and Phi 3 Small 8k Instruct share?
16 benchmarks have published results for both models. Nemotron 3 Ultra has 29 scored results on Noometry and Phi 3 Small 8k Instruct has 32.