Model comparison

Nemotron 4 340b Instruct vs Phi-2

Nemotron 4 340b Instruct has enough public results to be ranked (#218); Phi-2 does not yet, so treat this comparison as directional.

Last verified . 0 shared benchmarks.

Nemotron 4 340b Instruct NVIDIA

35.3

Rank #218 Confirmed

Phi-2 Microsoft

—

Unranked

Side by side

Nemotron 4 340b Instruct and Phi-2 specifications
Nemotron 4 340b InstructPhi-2
ProviderNVIDIAMicrosoft
Noometry Index35.3—
Released2024-06-142023-12-12
WeightsOpenOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked1711

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

Category by category

Coding Not comparable

Nemotron 4 340b Instruct: 34.6 (#223), Phi-2: —

Coding benchmarks
BenchmarkNemotron 4 340b InstructPhi-2
LMArena Coding1209—
HumanEval+—45.1%
MBPP+—54.2%

Reasoning Not comparable

Nemotron 4 340b Instruct: 22.4 (#180), Phi-2: —

Reasoning benchmarks
BenchmarkNemotron 4 340b InstructPhi-2
LMArena Hard Prompts1202—
Adversarial NLI—42.5%
BIG-Bench Hard—59.4%
Epoch Capabilities Index—107.62
HellaSwag—53.6%
WinoGrande—54.7%

Math Not comparable

Nemotron 4 340b Instruct: 31.7 (#193), Phi-2: —

Math benchmarks
BenchmarkNemotron 4 340b InstructPhi-2
LMArena Math1216—

Knowledge Not comparable

Nemotron 4 340b Instruct: 31.4 (#212), Phi-2: —

Knowledge benchmarks
BenchmarkNemotron 4 340b InstructPhi-2
LMArena Expert1171—
ARC (AI2) Challenge—75.9%
MMLU—58.4%
OpenBookQA—73.6%
TriviaQA—45.2%

Multilingual Not comparable

Nemotron 4 340b Instruct: 38.0 (#228), Phi-2: —

Multilingual benchmarks
BenchmarkNemotron 4 340b InstructPhi-2
LMArena Non-English1206—
LMArena Chinese1214—
LMArena French1196—
LMArena German1192—
LMArena Japanese1128—
LMArena Korean1148—
LMArena Russian1219—
LMArena Spanish1195—

Instruction Following Not comparable

Nemotron 4 340b Instruct: 63.3 (#227), Phi-2: —

Instruction Following benchmarks
BenchmarkNemotron 4 340b InstructPhi-2
LMArena Instruction Following1203—

Long Context Not comparable

Nemotron 4 340b Instruct: 37.1 (#216), Phi-2: —

Long Context benchmarks
BenchmarkNemotron 4 340b InstructPhi-2
LMArena Longer Query1225—

Writing & Preference Not comparable

Nemotron 4 340b Instruct: 42.9 (#229), Phi-2: —

Writing & Preference benchmarks
BenchmarkNemotron 4 340b InstructPhi-2
LMArena Text1225—
LMArena Creative Writing1203—
LMArena Multi-Turn1214—

Frequently asked questions

Is Nemotron 4 340b Instruct better than Phi-2?

Nemotron 4 340b Instruct has enough public results to be ranked (#218); Phi-2 does not yet, so treat this comparison as directional.

How many benchmarks do Nemotron 4 340b Instruct and Phi-2 share?

0 benchmarks have published results for both models. Nemotron 4 340b Instruct has 17 scored results on Noometry and Phi-2 has 11.

Related comparisons

Go deeper