Model comparison
Nemotron 3 Ultra vs Phi 3 Mini 4k Instruct June 2024
Nemotron 3 Ultra is the stronger model overall, scoring 44.7 to 30.7 on the Noometry Index.
Last verified . 14 shared benchmarks.
NVIDIA
MicrosoftSummary
- They share 14 benchmarks with published results for both. Nemotron 3 Ultra scores higher in 8 categories and Phi 3 Mini 4k Instruct June 2024 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 29.7.
Side by side
| Nemotron 3 Ultra | Phi 3 Mini 4k Instruct June 2024 | |
|---|---|---|
| Provider | NVIDIA | Microsoft |
| Noometry Index | 44.7 | 30.7 |
| Released | 2026-06-04 | — |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 128K | — |
| Input $ / M tokens | $0.60 | — |
| Output $ / M tokens | $2.40 | — |
| Results tracked | 29 | 15 |
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 Mini 4k Instruct June 2024: 31.2 (#275)
| Benchmark | Nemotron 3 Ultra | Phi 3 Mini 4k Instruct June 2024 |
|---|---|---|
| LMArena Coding | 1468 | 1093 |
| FrontierCode | 13.6% | — |
| SciCode | 40.3% | — |
| WeirdML | 43.5% | — |
Reasoning Nemotron 3 Ultra leads
Nemotron 3 Ultra: 30.3 (#78), Phi 3 Mini 4k Instruct June 2024: 19.9 (#229)
| Benchmark | Nemotron 3 Ultra | Phi 3 Mini 4k Instruct June 2024 |
|---|---|---|
| LMArena Hard Prompts | 1452 | 1088 |
| 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 leads
Nemotron 3 Ultra: 34.4 (#160), Phi 3 Mini 4k Instruct June 2024: 30.4 (#209)
| Benchmark | Nemotron 3 Ultra | Phi 3 Mini 4k Instruct June 2024 |
|---|---|---|
| LMArena Math | 1456 | 1152 |
| OTIS Mock AIME 2024-2025 | 86.7% | — |
| ProofBench | 2% | — |
Knowledge Nemotron 3 Ultra leads
Nemotron 3 Ultra: 52.5 (#56), Phi 3 Mini 4k Instruct June 2024: 28.1 (#240)
| Benchmark | Nemotron 3 Ultra | Phi 3 Mini 4k Instruct June 2024 |
|---|---|---|
| LMArena Expert | 1472 | 1051 |
| GPQA Diamond | 85.4% | — |
Multilingual Nemotron 3 Ultra leads
Nemotron 3 Ultra: 53.7 (#61), Phi 3 Mini 4k Instruct June 2024: 26.0 (#277)
| Benchmark | Nemotron 3 Ultra | Phi 3 Mini 4k Instruct June 2024 |
|---|---|---|
| LMArena Non-English | 1427 | 1013 |
| LMArena Chinese | 1498 | 1033 |
| LMArena German | 1471 | 1031 |
| LMArena Korean | 1387 | 880 |
| LMArena Russian | 1415 | 1019 |
| LMArena French | 1475 | — |
| LMArena Japanese | — | 954 |
| LMArena Spanish | 1452 | — |
Instruction Following Nemotron 3 Ultra leads
Nemotron 3 Ultra: 74.9 (#84), Phi 3 Mini 4k Instruct June 2024: 54.3 (#277)
| Benchmark | Nemotron 3 Ultra | Phi 3 Mini 4k Instruct June 2024 |
|---|---|---|
| LMArena Instruction Following | 1417 | 1058 |
Long Context Nemotron 3 Ultra leads
Nemotron 3 Ultra: 43.9 (#77), Phi 3 Mini 4k Instruct June 2024: 31.6 (#272)
| Benchmark | Nemotron 3 Ultra | Phi 3 Mini 4k Instruct June 2024 |
|---|---|---|
| LMArena Longer Query | 1437 | 1042 |
Writing & Preference Nemotron 3 Ultra leads
Nemotron 3 Ultra: 66.3 (#35), Phi 3 Mini 4k Instruct June 2024: 29.7 (#289)
| Benchmark | Nemotron 3 Ultra | Phi 3 Mini 4k Instruct June 2024 |
|---|---|---|
| LMArena Text | 1444 | 1080 |
| LMArena Creative Writing | 1392 | 1045 |
| LMArena Multi-Turn | 1412 | 1049 |
| EQ-Bench Creative Writing | 1692 | — |
Frequently asked questions
Is Nemotron 3 Ultra better than Phi 3 Mini 4k Instruct June 2024?
Nemotron 3 Ultra is the stronger model overall, scoring 44.7 to 30.7 on the Noometry Index.
Is Nemotron 3 Ultra or Phi 3 Mini 4k Instruct June 2024 better for coding?
Nemotron 3 Ultra scores higher on coding benchmarks: 37.7 versus 31.2 in the Noometry coding category.
How many benchmarks do Nemotron 3 Ultra and Phi 3 Mini 4k Instruct June 2024 share?
14 benchmarks have published results for both models. Nemotron 3 Ultra has 29 scored results on Noometry and Phi 3 Mini 4k Instruct June 2024 has 15.