LLMversus

Phi-3.5 Mini vs Yi-Large: Pricing, Benchmarks & Verdict (2026)

Pricing verified Sep 14, 2026By LLMversusUpdated September 17, 2026View methodology

⚡ Quick Answer

Compare Phi-3.5 Mini and Yi-Large across pricing, benchmarks, and capabilities.

Updated: September 14, 2026 · ✓ Pricing verified

Side-by-Side Comparison

FeaturePhi-3.5 MiniYi-Large
ProviderMicrosoft01.AI
Input Price / 1M tokens$0.130$3.00
Output Price / 1M tokens$0.520$3.00
Context Window
128K
32K
Max Output Tokens
4,096
4,096
Arena ELO
1,160
1,185
Coding ELO
1,165
1,195
TTFT (ms)
150
150
Tokens/sec
100
100
MultimodalNoNo
JSON ModeYesYes
Function CallingYesYes
VisionNoNo
When to Use Phi-3.5 Mini

Phi-3.5 Mini excels at cost-effective, fast-inference tasks.

Strengths:

  • Very cheap
  • Fast
  • Large context

Best for:

cost-effectivefast-inference
When to Use Yi-Large

Yi-Large excels at general-purpose, coding tasks.

Strengths:

  • Good quality
  • Fast
  • Balanced performance

Best for:

general-purposecoding

Related Comparisons

Claude Opus 4 vs Yi-LargeClaude Opus 4 vs Phi-3.5 MiniClaude Sonnet 4 vs Yi-LargeClaude Sonnet 4 vs Phi-3.5 MiniGemini 2 5 Pro vs Yi-LargeGemini 2 5 Pro vs Phi-3.5 MiniClaude Haiku 4 vs Yi-LargeClaude Haiku 4 vs Phi-3.5 MiniDeepseek R1 vs Yi-LargeDeepseek R1 vs Phi-3.5 MiniQwen 2 5 Max vs Yi-LargePhi-3.5 Mini vs Qwen 2 5 MaxGemini 2 0 Flash vs Yi-LargeGemini 2 0 Flash vs Phi-3.5 MiniDeepseek V3 vs Yi-LargeDeepseek V3 vs Phi-3.5 MiniO3 Mini vs Yi-LargeO3 Mini vs Phi-3.5 MiniO3 vs Yi-LargeO3 vs Phi-3.5 Mini