Model comparison

Nemotron 4 340b Instruct vs Phi-4

Nemotron 4 340b Instruct is the stronger model overall, scoring 35.3 to 30.9 on the Noometry Index.

Last verified . 17 shared benchmarks.

Nemotron 4 340b Instruct NVIDIA

35.3

Rank #218 Confirmed

Phi-4 Microsoft

30.9

Rank #269 Confirmed

Summary

  • They share 17 benchmarks with published results for both. Nemotron 4 340b Instruct scores higher in 7 categories and Phi-4 in 1 category; 5 gaps are clear of the uncertainty.
  • The widest gap is in math, where Nemotron 4 340b Instruct leads 31.7 to 19.6.

Side by side

Nemotron 4 340b Instruct and Phi-4 specifications
Nemotron 4 340b InstructPhi-4
ProviderNVIDIAMicrosoft
Noometry Index35.330.9
Released2024-06-142024-12-11
WeightsOpenOpen
Context window—128K
Max output—4K
Input $ / M tokens—$0.07
Output $ / M tokens—$0.14
Results tracked1737

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

Category by category

Coding Too close to call

Nemotron 4 340b Instruct: 34.6 (#223), Phi-4: 33.8 (#237)

Coding benchmarks
BenchmarkNemotron 4 340b InstructPhi-4
LMArena Coding12091231
BigCodeBench Instruct—45.5%
LiveBench Coding—30.7%
BigCodeBench Complete—55.4%

Agentic & Tool Use Not comparable

Nemotron 4 340b Instruct: —, Phi-4: 22.6 (#120)

Agentic & Tool Use benchmarks
BenchmarkNemotron 4 340b InstructPhi-4
Berkeley Function Calling Leaderboard—28.8%
BALROG—11.6%

Reasoning Nemotron 4 340b Instruct leads

Nemotron 4 340b Instruct: 22.4 (#180), Phi-4: 17.0 (#287)

Reasoning benchmarks
BenchmarkNemotron 4 340b InstructPhi-4
LMArena Hard Prompts12021220
Chess Puzzles—1%
LiveBench Reasoning—47.8%
LiveBench Data Analysis—45.2%
Epoch Capabilities Index—130.43
LiveBench—41.6%

Math Nemotron 4 340b Instruct leads

Nemotron 4 340b Instruct: 31.7 (#193), Phi-4: 19.6 (#279)

Math benchmarks
BenchmarkNemotron 4 340b InstructPhi-4
LMArena Math12161246
OTIS Mock AIME 2024-2025—13.8%
LiveBench Math—42%
MATH Level 5—64.9%

Knowledge Phi-4 leads

Nemotron 4 340b Instruct: 31.4 (#212), Phi-4: 32.5 (#204)

Knowledge benchmarks
BenchmarkNemotron 4 340b InstructPhi-4
LMArena Expert11711203
GPQA Diamond—56.1%
Confabulations—29.4%
Vectara Hallucination Rate—3.7%
MMLU—84.8%

Multilingual Too close to call

Nemotron 4 340b Instruct: 38.0 (#228), Phi-4: 37.4 (#232)

Multilingual benchmarks
BenchmarkNemotron 4 340b InstructPhi-4
LMArena Non-English12061197
LMArena Chinese12141211
LMArena French11961223
LMArena German11921222
LMArena Japanese11281158
LMArena Korean11481151
LMArena Russian12191209
LMArena Spanish11951234

Instruction Following Nemotron 4 340b Instruct leads

Nemotron 4 340b Instruct: 63.3 (#227), Phi-4: 60.6 (#246)

Instruction Following benchmarks
BenchmarkNemotron 4 340b InstructPhi-4
LMArena Instruction Following12031201
LiveBench Instruction Following—58.4%

Long Context Too close to call

Nemotron 4 340b Instruct: 37.1 (#216), Phi-4: 36.9 (#221)

Long Context benchmarks
BenchmarkNemotron 4 340b InstructPhi-4
LMArena Longer Query12251217

Writing & Preference Nemotron 4 340b Instruct leads

Nemotron 4 340b Instruct: 42.9 (#229), Phi-4: 40.7 (#239)

Writing & Preference benchmarks
BenchmarkNemotron 4 340b InstructPhi-4
LMArena Text12251217
LMArena Creative Writing12031182
LMArena Multi-Turn12141206
Short-Story Creative Writing—62.6%
LiveBench Language—25.6%

Frequently asked questions

Is Nemotron 4 340b Instruct better than Phi-4?

Nemotron 4 340b Instruct is the stronger model overall, scoring 35.3 to 30.9 on the Noometry Index.

Is Nemotron 4 340b Instruct or Phi-4 better for coding?

They score almost the same on coding (34.6 vs 33.8); test both on your own repository before choosing.

How many benchmarks do Nemotron 4 340b Instruct and Phi-4 share?

17 benchmarks have published results for both models. Nemotron 4 340b Instruct has 17 scored results on Noometry and Phi-4 has 37.

Related comparisons

Go deeper