Noometry

Model comparison

Llama 3.2 1B vs Phi-4

Phi-4 is the stronger model overall, scoring 31.2 to 20.1 on the Noometry Index.

Last verified . 21 shared benchmarks.

Llama 3.2 1B Meta

20.1

Rank #354 Confirmed

Phi-4 Microsoft

31.2

Rank #279 Confirmed

Summary

  • They share 21 benchmarks with published results for both. Llama 3.2 1B scores higher in 0 categories and Phi-4 in 9 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where Phi-4 leads 32.6 to 7.2.
  • The biggest single-benchmark swing is BigCodeBench Complete: 11.3% for Llama 3.2 1B and 55.4% for Phi-4.
  • Llama 3.2 1B is cheaper at $0.027 / $0.20 per million input/output tokens, against $0.07 / $0.14 for Phi-4.
  • Phi-4 accepts more context: 128K tokens versus 60K.

Side by side

Llama 3.2 1BPhi-4
ProviderMetaMicrosoft
Noometry Index20.131.2
Released2024-09-242024-12-11
WeightsOpenOpen
Context window60K128K
Max output54K4K
Input $ / M tokens$0.027$0.07
Output $ / M tokens$0.20$0.14
Results tracked2237

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

Category by category

Coding Phi-4 leads

Llama 3.2 1B: 21.1 (#338), Phi-4: 34.4 (#239)

BenchmarkLlama 3.2 1BPhi-4
BigCodeBench Instruct8.2%45.5%
LMArena Coding10701231
BigCodeBench Complete11.3%55.4%
LiveBench Coding—30.7%

Agentic & Tool Use Phi-4 leads

Llama 3.2 1B: 14.6 (#150), Phi-4: 22.8 (#128)

BenchmarkLlama 3.2 1BPhi-4
Berkeley Function Calling Leaderboard10.8%28.8%
BALROG6.6%11.6%

Reasoning Phi-4 leads

Llama 3.2 1B: 16.2 (#308), Phi-4: 17.7 (#291)

BenchmarkLlama 3.2 1BPhi-4
Chess Puzzles0%1%
LMArena Hard Prompts10441220
Epoch Capabilities Index101.99130.42
LiveBench Reasoning—47.8%
LiveBench Data Analysis—45.2%
LiveBench—41.6%

Math Phi-4 leads

Llama 3.2 1B: 10.4 (#313), Phi-4: 20.8 (#285)

BenchmarkLlama 3.2 1BPhi-4
OTIS Mock AIME 2024-20250.6%13.8%
LMArena Math10861246
LiveBench Math—42%
MATH Level 5—64.9%

Knowledge Phi-4 leads

Llama 3.2 1B: 7.2 (#312), Phi-4: 32.6 (#209)

BenchmarkLlama 3.2 1BPhi-4
GPQA Diamond23.9%56.1%
LMArena Expert10071203
Confabulations—29.4%
Vectara Hallucination Rate—3.7%
MMLU—84.8%

Multilingual Phi-4 leads

Llama 3.2 1B: 23.8 (#292), Phi-4: 37.2 (#237)

BenchmarkLlama 3.2 1BPhi-4
LMArena Non-English9731197
LMArena Chinese9591212
LMArena German10141222
LMArena Russian9411209
LMArena French—1224
LMArena Japanese—1158
LMArena Korean—1151
LMArena Spanish—1234

Instruction Following Phi-4 leads

Llama 3.2 1B: 52.4 (#290), Phi-4: 60.4 (#251)

BenchmarkLlama 3.2 1BPhi-4
LMArena Instruction Following10311201
LiveBench Instruction Following—58.4%

Long Context Phi-4 leads

Llama 3.2 1B: 31.9 (#274), Phi-4: 36.9 (#226)

BenchmarkLlama 3.2 1BPhi-4
LMArena Longer Query10501217

Writing & Preference Phi-4 leads

Llama 3.2 1B: 21.3 (#310), Phi-4: 40.5 (#244)

BenchmarkLlama 3.2 1BPhi-4
LMArena Text10551217
LMArena Creative Writing10331182
LMArena Multi-Turn10301206
Short-Story Creative Writing—62.6%
EQ-Bench Creative Writing200—
LiveBench Language—25.6%

Frequently asked questions

Is Llama 3.2 1B better than Phi-4?

Phi-4 is the stronger model overall, scoring 31.2 to 20.1 on the Noometry Index.

Which is cheaper, Llama 3.2 1B or Phi-4?

Llama 3.2 1B is cheaper. It lists at $0.027 per million input tokens and $0.20 per million output tokens; Phi-4 lists at $0.07 and $0.14.

Is Llama 3.2 1B or Phi-4 better for coding?

Phi-4 scores higher on coding benchmarks: 34.4 versus 21.1 in the Noometry coding category.

Which has the bigger context window?

Phi-4 does, with 128K tokens against 60K.

How many benchmarks do Llama 3.2 1B and Phi-4 share?

21 benchmarks have published results for both models. Llama 3.2 1B has 22 scored results on Noometry and Phi-4 has 37.

Related comparisons

Go deeper