Vascend
HorizonVascend IDEVascend CLICommunityBenchmarkContact
Sign inJoin Discord
HomeHorizonIDECLISign in
ChangelogIntelligenceCost per taskCoding Agent IndexCyber IndexDecision IndexBenchmarksSpeedLatencyPriceLeaderboard
Benchmark

Phi-4 Multimodal Instruct

  • Microsoft
  • Release · February 26, 2025
  • Open weights
  • Non-reasoning

Intelligence

Intelligence Index

#238 of 266
  1. 66Granite 4.0 H Small
  2. 5.95.9Nova Micro
  3. 5.95.9Phi-4
  4. 5.95.9LFM2 24B A2B
  5. 5.85.8NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)
  6. 5.85.8Phi-4 Multimodal Instruct
  7. 5.75.7MiniCPM-V 4.6 1.3B
  8. 5.75.7Jamba Reasoning 3B
  9. 5.65.6Olmo 3 7B Think
  10. 5.65.6Molmo 7B-D
Data from Artificial Analysis

Evaluations

  • Humanity's Last Exam5%#210
  • MMMU-Pro14.5%#121
  • GPQA Diamond31.5%#198
Phi-4 Multimodal InstructMedian
Data from Artificial Analysis

Speed and price

Price

$ per 1M tokens (3:1) · #25 of 169
  1. $0.10.1Ministral 3 3B
  2. $0.110.11Granite 4.2 8B
  3. $0.130.13Apertus 8B Instruct
  4. $0.130.13gpt-oss-20b (Low)
  5. $0.130.13Phi-4 Mini Instruct
  6. $0.140.14Phi-4 Multimodal Instruct
  7. $0.150.15Agnes 2.5 Pro Beta
  8. $0.150.15Gemma 4 12B (Reasoning)
  9. $0.150.15Gemma 4 12B (Non-reasoning)
  10. $0.150.15Ministral 3 8B
Data from Artificial Analysis

Nearby models

  • Granite 4.0 H SmallIBM6
  • Nova MicroAmazon5.9
  • Phi-4Microsoft5.9
  • LFM2 24B A2BLiquid AI5.9
  • NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)NVIDIA5.8
  • MiniCPM-V 4.6 1.3BOpenBMB5.7
  • Jamba Reasoning 3BAI21 Labs5.7
  • Olmo 3 7B ThinkAllen Institute for AI5.6
Data from Artificial Analysis

Same lab

  • Phi-4 Mini InstructMicrosoft6.3
Data from Artificial Analysis
HorizonVascend IDEOlympusTalosCoursesCommunityBenchmark
DiscordGitHubXLet’s talkLegalPrivacyCookiesData useSecurity
© 2026 Vascend Technologies · VAT IT04911550616
ascend