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

Ministral 3 14B

  • Mistral
  • Release · December 2, 2025
  • Open weights
  • Non-reasoning

Intelligence

Intelligence Index

#231 of 266
  1. 6.36.3Phi-4 Mini Instruct
  2. 6.26.2Qwen3.5 2B (Non-reasoning)
  3. 6.16.1DeepHermes 3 - Mistral 24B Preview (Non-reasoning)
  4. 6.16.1Jamba 1.7 Large
  5. 6.16.1Qwen3.5 0.8B (Reasoning)
  6. 66Ministral 3 14B
  7. 66Qwen3 Omni 30B A3B Instruct
  8. 66Granite 4.0 H Small
  9. 5.95.9Nova Micro
  10. 5.95.9Phi-4
Data from Artificial Analysis

Evaluations

  • AA-Omniscience Accuracy13.6%#193
  • Humanity's Last Exam4.6%#224
  • Terminal-Bench 4.00%#96
  • AA-LCR26.3%#180
  • SciCode23.8%#132
  • CritPt0%#143
  • MMMU-Pro49.8%#103
  • GPQA Diamond57.2%#150
  • IFBench32%#118
  • τ²-Bench Telecom27.2%#86
  • τ²-Bench Banking6.6%#78
  • Terminal-Bench Hard4.6%#81
Ministral 3 14BMedian
Data from Artificial Analysis

Speed and price

Speed

tokens per second · #111 of 162
  1. 8181Gemini 4 Argon (High)
  2. 8181Hy3
  3. 8080Claude Opus 5.5 (High)
  4. 8080Qwen3.5 9B (Non-reasoning)
  5. 7878Grok 4.7 (Low)
  6. 7777Ministral 3 14B
  7. 7777Magistral Small 1.2
  8. 7676LongCat 2.0
  9. 7070GLM-5.3-Flash
  10. 7070Claude Fable 5.1 (Max)
Data from Artificial Analysis

Latency

seconds to first token · #38 of 162
  1. 0.90.9Qwen3 Coder Next
  2. 0.90.9Mistral Small 4 (Non-reasoning)
  3. 11Gemma 4 26B A4B (Non-reasoning)
  4. 11gpt-oss-20b (Low)
  5. 11NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)
  6. 11Ministral 3 14B
  7. 11Claude Sonnet 5.5 (Low)
  8. 11Llama 4 Maverick
  9. 11Nova 2.0 Pro Preview (Non-reasoning)
  10. 11Nova 2.0 Lite (Non-reasoning)
Data from Artificial Analysis

Price

$ per 1M tokens (3:1) · #48 of 169
  1. $0.20.2GPT-6 Luna (High)
  2. $0.20.2GPT-6 Luna (Medium)
  3. $0.20.2Claude Haiku 5.5 (Low)
  4. $0.20.2GPT-6 Luna (Low)
  5. $0.20.2GPT-6 Luna (Non-reasoning)
  6. $0.20.2Ministral 3 14B
  7. $0.220.22Phi-4
  8. $0.220.22Gemma 4 31B (Non-reasoning)
  9. $0.230.23Qwen3.8-Flash-Next
  10. $0.240.24GLM-5.3-Flash
Data from Artificial Analysis

Nearby models

  • Phi-4 Mini InstructMicrosoft6.3
  • Qwen3.5 2B (Non-reasoning)Alibaba6.2
  • DeepHermes 3 - Mistral 24B Preview (Non-reasoning)Nous Research6.1
  • Jamba 1.7 LargeAI21 Labs6.1
  • Qwen3.5 0.8B (Reasoning)Alibaba6.1
  • Qwen3 Omni 30B A3B InstructAlibaba6
  • Granite 4.0 H SmallIBM6
  • Nova MicroAmazon5.9
Data from Artificial Analysis

Same lab

  • Mistral Large 4 PreviewMistral38.4
  • Mistral Medium 3.5Mistral14.2
  • Magistral Medium 1.2Mistral11.8
  • Mistral Small 4 (Reasoning)Mistral11.3
  • Mistral Small 4 (Non-reasoning)Mistral9
  • Magistral Small 1.2Mistral8.6
  • Ministral 3 8BMistral5.5
  • Ministral 3 3BMistral4.8
Data from Artificial Analysis
HorizonVascend IDEOlympusTalosCoursesCommunityBenchmark
DiscordGitHubXLet’s talkLegalPrivacyCookiesData useSecurity
© 2026 Vascend Technologies · VAT IT04911550616
ascend