Model comparison
Nemotron 3 Super vs Phi-4
Nemotron 3 Super is the stronger model overall, scoring 40.1 to 31.2 on the Noometry Index. Phi-4 costs 2.0× less per token, which makes it the better buy when Nemotron 3 Super's lead doesn't matter for your workload.
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-4 in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Nemotron 3 Super leads 39.6 to 20.8.
- Phi-4 is cheaper at $0.07 / $0.14 per million input/output tokens, against $0.08 / $0.45 for Nemotron 3 Super.
- Nemotron 3 Super accepts more context: 262K tokens versus 128K.
Side by side
| Nemotron 3 Super | Phi-4 | |
|---|---|---|
| Provider | NVIDIA | Microsoft |
| Noometry Index | 40.1 | 31.2 |
| Released | 2026-03-11 | 2024-12-11 |
| Weights | Open | Open |
| Context window | 262K | 128K |
| Max output | 131K | 4K |
| Input $ / M tokens | $0.08 | $0.07 |
| Output $ / M tokens | $0.45 | $0.14 |
| Results tracked | 21 | 37 |
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-4: 34.4 (#239)
| Benchmark | Nemotron 3 Super | Phi-4 |
|---|---|---|
| LMArena Coding | 1403 | 1231 |
| SciCode | 36% | — |
| WeirdML | 38% | — |
| BigCodeBench Instruct | — | 45.5% |
| LiveBench Coding | — | 30.7% |
| BigCodeBench Complete | — | 55.4% |
| ALE-Bench | 213.9 | — |
Agentic & Tool Use Not comparable
Nemotron 3 Super: —, Phi-4: 22.8 (#128)
| Benchmark | Nemotron 3 Super | Phi-4 |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 28.8% |
| BALROG | — | 11.6% |
Reasoning Nemotron 3 Super leads
Nemotron 3 Super: 18.7 (#276), Phi-4: 17.7 (#291)
| Benchmark | Nemotron 3 Super | Phi-4 |
|---|---|---|
| LMArena Hard Prompts | 1386 | 1220 |
| NYT Connections (extended) | 15.4% | — |
| CritPt | 3.1% | — |
| Chess Puzzles | — | 1% |
| LiveBench Reasoning | — | 47.8% |
| LiveBench Data Analysis | — | 45.2% |
| Epoch Capabilities Index | — | 130.42 |
| LiveBench | — | 41.6% |
Math Nemotron 3 Super leads
Nemotron 3 Super: 39.6 (#101), Phi-4: 20.8 (#285)
| Benchmark | Nemotron 3 Super | Phi-4 |
|---|---|---|
| LMArena Math | 1380 | 1246 |
| MathArena Final-Answer Competitions | 60.4% | — |
| OTIS Mock AIME 2024-2025 | — | 13.8% |
| LiveBench Math | — | 42% |
| MATH Level 5 | — | 64.9% |
Knowledge Nemotron 3 Super leads
Nemotron 3 Super: 38.9 (#139), Phi-4: 32.6 (#209)
| Benchmark | Nemotron 3 Super | Phi-4 |
|---|---|---|
| LMArena Expert | 1398 | 1203 |
| GPQA Diamond | — | 56.1% |
| Confabulations | — | 29.4% |
| Vectara Hallucination Rate | — | 3.7% |
| MMLU | — | 84.8% |
Multilingual Nemotron 3 Super leads
Nemotron 3 Super: 48.4 (#144), Phi-4: 37.2 (#237)
| Benchmark | Nemotron 3 Super | Phi-4 |
|---|---|---|
| LMArena Non-English | 1355 | 1197 |
| LMArena Chinese | 1432 | 1212 |
| LMArena French | 1405 | 1224 |
| LMArena German | 1341 | 1222 |
| LMArena Russian | 1336 | 1209 |
| LMArena Spanish | 1417 | 1234 |
| LMArena Japanese | — | 1158 |
| LMArena Korean | — | 1151 |
Instruction Following Nemotron 3 Super leads
Nemotron 3 Super: 71.2 (#154), Phi-4: 60.4 (#251)
| Benchmark | Nemotron 3 Super | Phi-4 |
|---|---|---|
| LMArena Instruction Following | 1347 | 1201 |
| LiveBench Instruction Following | — | 58.4% |
Long Context Nemotron 3 Super leads
Nemotron 3 Super: 41.5 (#139), Phi-4: 36.9 (#226)
| Benchmark | Nemotron 3 Super | Phi-4 |
|---|---|---|
| LMArena Longer Query | 1362 | 1217 |
Writing & Preference Nemotron 3 Super leads
Nemotron 3 Super: 55.9 (#140), Phi-4: 40.5 (#244)
| Benchmark | Nemotron 3 Super | Phi-4 |
|---|---|---|
| LMArena Text | 1378 | 1217 |
| LMArena Creative Writing | 1317 | 1182 |
| LMArena Multi-Turn | 1369 | 1206 |
| Short-Story Creative Writing | — | 62.6% |
| LiveBench Language | — | 25.6% |
Frequently asked questions
Is Nemotron 3 Super better than Phi-4?
Nemotron 3 Super is the stronger model overall, scoring 40.1 to 31.2 on the Noometry Index. Phi-4 costs 2.0× less per token, which makes it the better buy when Nemotron 3 Super's lead doesn't matter for your workload.
Which is cheaper, Nemotron 3 Super or Phi-4?
Phi-4 is cheaper. It lists at $0.07 per million input tokens and $0.14 per million output tokens; Nemotron 3 Super lists at $0.08 and $0.45.
Is Nemotron 3 Super or Phi-4 better for coding?
Nemotron 3 Super scores higher on coding benchmarks: 39.4 versus 34.4 in the Noometry coding category.
Which has the bigger context window?
Nemotron 3 Super does, with 262K tokens against 128K.
How many benchmarks do Nemotron 3 Super and Phi-4 share?
15 benchmarks have published results for both models. Nemotron 3 Super has 21 scored results on Noometry and Phi-4 has 37.