Model comparison

Llama 3.2 90B vs Phi-1.5

Llama 3.2 90B has enough public results to be ranked (#326); Phi-1.5 does not yet, so treat this comparison as directional.

Last verified . 2 shared benchmarks.

Llama 3.2 90B Meta

27.1

Rank #326 Confirmed

Phi-1.5 Microsoft

—

Unranked

Summary

  • They share 2 benchmarks with published results for both.

Side by side

Llama 3.2 90B and Phi-1.5 specifications
Llama 3.2 90BPhi-1.5
ProviderMetaMicrosoft
Noometry Index27.1—
Released2024-09-242023-09-11
WeightsOpenOpen
Context window——
Max output——
Input $ / M tokens——
Output $ / M tokens——
Results tracked97

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

Category by category

Agentic & Tool Use Not comparable

Llama 3.2 90B: 29.7 (#73), Phi-1.5: —

Agentic & Tool Use benchmarks
BenchmarkLlama 3.2 90BPhi-1.5
BALROG27.3%—

Reasoning Not comparable

Llama 3.2 90B: 20.9 (#207), Phi-1.5: —

Reasoning benchmarks
BenchmarkLlama 3.2 90BPhi-1.5
Epoch Capabilities Index125.590.82
EnigmaEval0.4%—
HellaSwag—47.6%
WinoGrande—73.4%

Math Not comparable

Llama 3.2 90B: 10.4 (#302), Phi-1.5: —

Math benchmarks
BenchmarkLlama 3.2 90BPhi-1.5
OTIS Mock AIME 2024-20252.6%—
MATH Level 539.4%—

Knowledge Not comparable

Llama 3.2 90B: 21.7 (#269), Phi-1.5: —

Knowledge benchmarks
BenchmarkLlama 3.2 90BPhi-1.5
MMLU80.3%37.6%
GPQA Diamond41%—
ARC (AI2) Challenge—44.4%
BoolQ—75.8%
OpenBookQA—37.2%

Multimodal Not comparable

Llama 3.2 90B: 24.9 (#119), Phi-1.5: —

Multimodal benchmarks
BenchmarkLlama 3.2 90BPhi-1.5
LMArena Vision1000—
GeoBench52%—

Frequently asked questions

Is Llama 3.2 90B better than Phi-1.5?

Llama 3.2 90B has enough public results to be ranked (#326); Phi-1.5 does not yet, so treat this comparison as directional.

How many benchmarks do Llama 3.2 90B and Phi-1.5 share?

2 benchmarks have published results for both models. Llama 3.2 90B has 9 scored results on Noometry and Phi-1.5 has 7.

Related comparisons

Go deeper