Noometry

Model comparison

Nemotron 3 Ultra vs Phi-4 Mini

Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 30.9 on the Noometry Index. Phi-4 Mini costs 7.0× less per token, which makes it the better buy when Nemotron 3 Ultra's lead doesn't matter for your workload.

Last verified . 2 shared benchmarks.

Nemotron 3 Ultra NVIDIA

42.5

Rank #113 Confirmed

Phi-4 Mini Microsoft

30.9

Rank #283 Reported

Summary

  • They share 2 benchmarks with published results for both. Nemotron 3 Ultra scores higher in 3 categories and Phi-4 Mini in 0 categories; 3 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Nemotron 3 Ultra leads 52.5 to 25.3.
  • The biggest single-benchmark swing is SciCode: 40.3% for Nemotron 3 Ultra and 10.8% for Phi-4 Mini.
  • Phi-4 Mini is cheaper at $0.075 / $0.30 per million input/output tokens, against $0.50 / $2.20 for Nemotron 3 Ultra.
  • Nemotron 3 Ultra accepts more context: 262K tokens versus 128K.

Side by side

Nemotron 3 UltraPhi-4 Mini
ProviderNVIDIAMicrosoft
Noometry Index42.530.9
Released2026-06-042024-12-11
WeightsOpenOpen
Context window262K128K
Max output128K4K
Input $ / M tokens$0.50$0.075
Output $ / M tokens$2.20$0.30
Results tracked303

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Nemotron 3 Ultra leads

Nemotron 3 Ultra: 38.1 (#182), Phi-4 Mini: 28.1 (#317)

BenchmarkNemotron 3 UltraPhi-4 Mini
SciCode40.3%10.8%
FrontierCode13.6%—
WeirdML43.5%—
LMArena Coding1468—

Agentic & Tool Use Not comparable

Nemotron 3 Ultra: 23.4 (#126), Phi-4 Mini: —

BenchmarkNemotron 3 UltraPhi-4 Mini
APEX-Agents22.7%—

Reasoning Nemotron 3 Ultra leads

Nemotron 3 Ultra: 31.0 (#82), Phi-4 Mini: 22.4 (#195)

BenchmarkNemotron 3 UltraPhi-4 Mini
CritPt3.1%0%
Chess Puzzles12%—
LMArena Hard Prompts1452—
Mystery Game Puzzles20%—
DTBench90.1%—
LMCA36.9%—
Epoch Capabilities Index146.17—

Math Not comparable

Nemotron 3 Ultra: 35.3 (#187), Phi-4 Mini: —

BenchmarkNemotron 3 UltraPhi-4 Mini
OTIS Mock AIME 2024-202586.7%—
ProofBench2%—
LMArena Math1457—

Knowledge Nemotron 3 Ultra leads

Nemotron 3 Ultra: 52.5 (#61), Phi-4 Mini: 25.3 (#262)

BenchmarkNemotron 3 UltraPhi-4 Mini
GPQA Diamond85.4%—
Vectara Hallucination Rate—23.5%
LMArena Expert1472—

Multilingual Not comparable

Nemotron 3 Ultra: 53.5 (#64), Phi-4 Mini: —

BenchmarkNemotron 3 UltraPhi-4 Mini
LMArena Non-English1427—
LMArena Chinese1497—
LMArena French1472—
LMArena German1471—
LMArena Korean1386—
LMArena Russian1417—
LMArena Spanish1454—

Instruction Following Not comparable

Nemotron 3 Ultra: 74.7 (#88), Phi-4 Mini: —

BenchmarkNemotron 3 UltraPhi-4 Mini
LMArena Instruction Following1418—

Long Context Not comparable

Nemotron 3 Ultra: 43.9 (#81), Phi-4 Mini: —

BenchmarkNemotron 3 UltraPhi-4 Mini
LMArena Longer Query1437—

Writing & Preference Not comparable

Nemotron 3 Ultra: 66.3 (#36), Phi-4 Mini: —

BenchmarkNemotron 3 UltraPhi-4 Mini
LMArena Text1445—
LMArena Creative Writing1398—
EQ-Bench Creative Writing1692—
LMArena Multi-Turn1411—

Frequently asked questions

Is Nemotron 3 Ultra better than Phi-4 Mini?

Nemotron 3 Ultra is the stronger model overall, scoring 42.5 to 30.9 on the Noometry Index. Phi-4 Mini costs 7.0× less per token, which makes it the better buy when Nemotron 3 Ultra's lead doesn't matter for your workload.

Which is cheaper, Nemotron 3 Ultra or Phi-4 Mini?

Phi-4 Mini is cheaper. It lists at $0.075 per million input tokens and $0.30 per million output tokens; Nemotron 3 Ultra lists at $0.50 and $2.20.

Is Nemotron 3 Ultra or Phi-4 Mini better for coding?

Nemotron 3 Ultra scores higher on coding benchmarks: 38.1 versus 28.1 in the Noometry coding category.

Which has the bigger context window?

Nemotron 3 Ultra does, with 262K tokens against 128K.

How many benchmarks do Nemotron 3 Ultra and Phi-4 Mini share?

2 benchmarks have published results for both models. Nemotron 3 Ultra has 30 scored results on Noometry and Phi-4 Mini has 3.

Related comparisons

Go deeper