token.app › Compare › Mistral Small 3.1 24B vs Phi 4

Mistral Small 3.1 24B vs Phi 4

Phi 4 leads on 2 of 2 shared benchmarks. Phi 4 is 4.6× cheaper per token on a blended 3:1 basis. Mistral Small 3.1 24B accepts the larger context window (128K).

Head to head
Blended price uses a 3:1 input:output mix
Mistral Small 3.1 24BPhi 4
ProviderMistral AIMicrosoft
Input $/1M$0.351$0.070
Output $/1M$0.555$0.140
Blended $/1M$0.402$0.088
Context window128K16K
Max output128K16K
ReleasedMar 2025Jan 2025
LicenceOpen weightsOpen weights
GPQA Diamond 47.5% 56.1%
OTIS Mock AIME 5.8% 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 Mistral Small 3.1 24B if…
  • Larger context window (128K)
  • Newer model (released Mar 2025)
Choose Phi 4 if…
  • Costs less per token — $0.088 vs $0.402 blended
  • Higher GPQA Diamond (56.1% vs 47.5%)
  • Higher OTIS Mock AIME (13.8% vs 5.8%)
FAQ
Which is better, Mistral Small 3.1 24B or Phi 4?
Across the 2 benchmarks both models have independently-run scores for, Mistral Small 3.1 24B leads on 0 and Phi 4 leads on 2. Benchmarks are one input — price and context window are on this page too.
Is Mistral Small 3.1 24B cheaper than Phi 4?
Phi 4 is cheaper: $0.088 versus $0.402 per million tokens blended at 3:1 input:output. Input alone: $0.351 vs $0.070. Output alone: $0.555 vs $0.140.
What context windows do Mistral Small 3.1 24B and Phi 4 have?
Mistral Small 3.1 24B: 128,000 tokens. Phi 4: 16,384 tokens.
Who makes Mistral Small 3.1 24B and Phi 4?
Mistral Small 3.1 24B is made by Mistral AI. Phi 4 is made by Microsoft.
Related comparisons
Mistral Small 3.1 24B full details Phi 4 full details Mistral Small 3.1 24B vs Ling 3.0 Tiny (free) Mistral Small 3.1 24B vs Muse Spark 1.2 Mistral Small 3.1 24B vs Qwen3.8 Max Mistral Small 3.1 24B vs DeepSeek V4 Flash Latest Mistral Small 3.1 24B vs DeepSeek V4 Flash 0731 Mistral Small 3.1 24B vs Inkling Small