token.app › Compare › Llama 4 Scout vs Phi 4

Llama 4 Scout vs Phi 4

Phi 4 leads on 2 of 2 shared benchmarks. Phi 4 is 1.7× cheaper per token on a blended 3:1 basis. Llama 4 Scout accepts the larger context window (1.3M).

Head to head
Blended price uses a 3:1 input:output mix
Llama 4 ScoutPhi 4
ProviderMetaMicrosoft
Input $/1M$0.100$0.070
Output $/1M$0.300$0.140
Blended $/1M$0.150$0.088
Context window1.3M16K
Max output16K16K
ReleasedApr 2025Jan 2025
LicenceOpen weightsOpen weights
GPQA Diamond 51.8% 56.1%
OTIS Mock AIME 7.8% 13.8%
Benchmark scores independently run and published by Epoch AI, 'AI Benchmarking Hub', used under CC BY 4.0. Only benchmarks with a score for BOTH models are compared.
Choose Llama 4 Scout if…
  • Larger context window (1.3M)
  • Newer model (released Apr 2025)
Choose Phi 4 if…
  • Costs less per token — $0.088 vs $0.150 blended
  • Higher GPQA Diamond (56.1% vs 51.8%)
  • Higher OTIS Mock AIME (13.8% vs 7.8%)
FAQ
Which is better, Llama 4 Scout or Phi 4?
Across the 2 benchmarks both models have independently-run scores for, Llama 4 Scout leads on 0 and Phi 4 leads on 2. Benchmarks are one input — price and context window are on this page too.
Is Llama 4 Scout cheaper than Phi 4?
Phi 4 is cheaper: $0.088 versus $0.150 per million tokens blended at 3:1 input:output. Input alone: $0.100 vs $0.070. Output alone: $0.300 vs $0.140.
What context windows do Llama 4 Scout and Phi 4 have?
Llama 4 Scout: 1,310,720 tokens. Phi 4: 16,384 tokens.
Who makes Llama 4 Scout and Phi 4?
Llama 4 Scout is made by Meta. Phi 4 is made by Microsoft.
Related comparisons