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

Ministral 3 3B

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

Intelligence

Intelligence Index

#262 of 266
  1. 5.15.1Granite 4.0 Micro
  2. 55Molmo2-8B
  3. 4.84.8Granite 4.0 H 350M
  4. 4.84.8Granite 4.0 350M
  5. 4.84.8NVIDIA Nemotron 3 Nano 4B
  6. 4.84.8Ministral 3 3B
  7. 4.84.8Tiny Aya Global
  8. 4.84.8Apertus 8B Instruct
  9. 4.84.8LFM2.5-VL-1.6B
  10. 33K2 Horizon 0.9B
Data from Artificial Analysis

Evaluations

  • AA-Omniscience Accuracy9%#228
  • Humanity's Last Exam5.4%#201
  • Terminal-Bench 4.00%#96
  • AA-LCR17%#200
  • SciCode15.3%#138
  • CritPt0%#143
  • MMMU-Pro38.1%#113
  • GPQA Diamond35.8%#190
  • IFBench26.8%#135
  • τ²-Bench Telecom24.9%#94
  • τ²-Bench Banking4.7%#91
  • Terminal-Bench Hard0%#121
Ministral 3 3BMedian
Data from Artificial Analysis

Speed and price

Speed

tokens per second · #20 of 162
  1. 232232Qwen3.5 Omni Flash
  2. 231231Nemotron 3 Nano Omni 30B A3B Reasoning
  3. 229229Step 5 Preview
  4. 223223Inkling Small
  5. 213213Ling 3.1 Flash
  6. 209209Ministral 3 3B
  7. 202202NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)
  8. 195195Inkling (Xhigh)
  9. 189189Sarvam 105B (High)
  10. 186186Nova 2.0 Lite (High)
Data from Artificial Analysis

Latency

seconds to first token · #6 of 162
  1. 0.50.5North Mini Code
  2. 0.50.5Command A+
  3. 0.60.6Celeris-1
  4. 0.60.6Nemotron 3.5 Lightning
  5. 0.60.6NVIDIA Nemotron Nano 9B V2 (Reasoning)
  6. 0.70.7Ministral 3 3B
  7. 0.70.7Beam 1.0
  8. 0.70.7Nemotron 3.5 Super VL
  9. 0.70.7Granite 4.2 3B
  10. 0.80.8GPT-5.6 Terra (Non-reasoning)
Data from Artificial Analysis

Price

$ per 1M tokens (3:1) · #20 of 169
  1. $0.090.09NVIDIA Nemotron Nano 9B V2 (Non-reasoning)
  2. $0.090.09NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)
  3. $0.090.09NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)
  4. $0.090.09gpt-oss-20b (High)
  5. $0.10.1Nemotron 3.5 Lightning
  6. $0.10.1Ministral 3 3B
  7. $0.110.11Granite 4.2 8B
  8. $0.130.13Apertus 8B Instruct
  9. $0.130.13gpt-oss-20b (Low)
  10. $0.130.13Phi-4 Mini Instruct
Data from Artificial Analysis

Nearby models

  • Granite 4.0 MicroIBM5.1
  • Molmo2-8BAllen Institute for AI5
  • Granite 4.0 H 350MIBM4.8
  • Granite 4.0 350MIBM4.8
  • NVIDIA Nemotron 3 Nano 4BNVIDIA4.8
  • Tiny Aya GlobalCohere4.8
  • Apertus 8B InstructSwiss AI Initiative4.8
  • LFM2.5-VL-1.6BLiquid AI4.8
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 14BMistral6
  • Ministral 3 8BMistral5.5
Data from Artificial Analysis
HorizonVascend IDEOlympusTalosCoursesCommunityBenchmark
DiscordGitHubXLet’s talkLegalPrivacyCookiesData useSecurity
© 2026 Vascend Technologies · VAT IT04911550616
ascend