Model comparison
Nemotron 3 Super vs Phi 3 Mini 4k Instruct
Nemotron 3 Super is the stronger model overall, scoring 40.1 to 27.9 on the Noometry Index.
Last verified . 15 shared benchmarks.
NVIDIA
MicrosoftSummary
- They share 15 benchmarks with published results for both. Nemotron 3 Super scores higher in 8 categories and Phi 3 Mini 4k Instruct in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Nemotron 3 Super leads 55.9 to 27.6.
Side by side
| Nemotron 3 Super | Phi 3 Mini 4k Instruct | |
|---|---|---|
| Provider | NVIDIA | Microsoft |
| Noometry Index | 40.1 | 27.9 |
| Released | 2026-03-11 | 2024-04-23 |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.08 | — |
| Output $ / M tokens | $0.45 | — |
| Results tracked | 21 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Nemotron 3 Super leads
Nemotron 3 Super: 39.4 (#158), Phi 3 Mini 4k Instruct: 26.6 (#323)
| Benchmark | Nemotron 3 Super | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Coding | 1403 | 1093 |
| SciCode | 36% | — |
| WeirdML | 38% | — |
| LiveBench Coding | — | 15.5% |
| ALE-Bench | 213.9 | — |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 54.2% |
Reasoning Nemotron 3 Super leads
Nemotron 3 Super: 18.7 (#276), Phi 3 Mini 4k Instruct: 14.1 (#328)
| Benchmark | Nemotron 3 Super | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1386 | 1072 |
| NYT Connections (extended) | 15.4% | — |
| CritPt | 3.1% | — |
| Chess Puzzles | — | 0% |
| LiveBench Reasoning | — | 26.8% |
| LiveBench Data Analysis | — | 34.7% |
| Adversarial NLI | — | 52.8% |
| BIG-Bench Hard | — | 71.7% |
| HellaSwag | — | 76.7% |
| LiveBench | — | 22.4% |
| WinoGrande | — | 70.8% |
Math Nemotron 3 Super leads
Nemotron 3 Super: 39.6 (#101), Phi 3 Mini 4k Instruct: 26.6 (#257)
| Benchmark | Nemotron 3 Super | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Math | 1380 | 1111 |
| MathArena Final-Answer Competitions | 60.4% | — |
| LiveBench Math | — | 15.7% |
Knowledge Nemotron 3 Super leads
Nemotron 3 Super: 38.9 (#139), Phi 3 Mini 4k Instruct: 28.5 (#246)
| Benchmark | Nemotron 3 Super | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Expert | 1398 | 1045 |
| ARC (AI2) Challenge | — | 84.9% |
| MMLU | — | 68.8% |
| OpenBookQA | — | 88% |
| TriviaQA | — | 64% |
Multilingual Nemotron 3 Super leads
Nemotron 3 Super: 48.4 (#144), Phi 3 Mini 4k Instruct: 26.3 (#280)
| Benchmark | Nemotron 3 Super | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Non-English | 1355 | 1021 |
| LMArena Chinese | 1432 | 1021 |
| LMArena French | 1405 | 1076 |
| LMArena German | 1341 | 1044 |
| LMArena Russian | 1336 | 1022 |
| LMArena Spanish | 1417 | 1085 |
| LMArena Japanese | — | 935 |
| LMArena Korean | — | 905 |
Instruction Following Nemotron 3 Super leads
Nemotron 3 Super: 71.2 (#154), Phi 3 Mini 4k Instruct: 47.7 (#303)
| Benchmark | Nemotron 3 Super | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1347 | 1053 |
| LiveBench Instruction Following | — | 39.1% |
Long Context Nemotron 3 Super leads
Nemotron 3 Super: 41.5 (#139), Phi 3 Mini 4k Instruct: 31.7 (#276)
| Benchmark | Nemotron 3 Super | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1362 | 1044 |
Writing & Preference Nemotron 3 Super leads
Nemotron 3 Super: 55.9 (#140), Phi 3 Mini 4k Instruct: 27.6 (#300)
| Benchmark | Nemotron 3 Super | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Text | 1378 | 1073 |
| LMArena Creative Writing | 1317 | 1037 |
| LMArena Multi-Turn | 1369 | 1018 |
| LiveBench Language | — | 9.2% |
Frequently asked questions
Is Nemotron 3 Super better than Phi 3 Mini 4k Instruct?
Nemotron 3 Super is the stronger model overall, scoring 40.1 to 27.9 on the Noometry Index.
Is Nemotron 3 Super or Phi 3 Mini 4k Instruct better for coding?
Nemotron 3 Super scores higher on coding benchmarks: 39.4 versus 26.6 in the Noometry coding category.
How many benchmarks do Nemotron 3 Super and Phi 3 Mini 4k Instruct share?
15 benchmarks have published results for both models. Nemotron 3 Super has 21 scored results on Noometry and Phi 3 Mini 4k Instruct has 35.