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

Mistral Small 4 (Non-reasoning)

  • Mistral
  • Open weights
  • Non-reasoning

Intelligence

Intelligence Index

#180 of 266
  1. 9.29.2Qwen3 Coder Next
  2. 9.29.2Motif-2-12.7B-Reasoning
  3. 9.29.2Nova Premier
  4. 9.19.1Granite 4.2 3B
  5. 99gpt-oss-20b (High)
  6. 99Mistral Small 4 (Non-reasoning)
  7. 99K2-V2 (Medium)
  8. 99Tri-21B-Think
  9. 8.98.9Gemma 4 E4B (Reasoning)
  10. 8.98.9NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)
Data from Artificial Analysis

Evaluations

  • AA-Omniscience Accuracy16.6%#155
  • Humanity's Last Exam3.8%#248
  • AA-LCR28.3%#175
  • CritPt0.3%#117
  • MMMU-Pro46.5%#105
  • GPQA Diamond57.1%#152
  • IFBench32.8%#115
  • τ²-Bench Telecom18.4%#115
  • Terminal-Bench Hard10.6%#57
Mistral Small 4 (Non-reasoning)Median
Data from Artificial Analysis

Speed and price

Speed

tokens per second · #33 of 162
  1. 181181Claude Haiku 5.5 (High)
  2. 180180Nova 2.0 Lite (Medium)
  3. 179179Claude Haiku 5.5 (Medium)
  4. 178178Mistral Small 4 (Reasoning)
  5. 177177DeepSeek V4 Flash Vision (Max)
  6. 173173Mistral Small 4 (Non-reasoning)
  7. 173173Claude Haiku 5.5 (Low)
  8. 173173gpt-oss-20b (High)
  9. 173173Nova 2.0 Lite (Low)
  10. 169169DeepSeek V4.1 Flash 1017 (Max)
Data from Artificial Analysis

Latency

seconds to first token · #34 of 162
  1. 0.90.9Qwen3.5 4B (Non-reasoning)
  2. 0.90.9Gemma 4 E4B (Reasoning)
  3. 0.90.9Gemma 4 26B A4B (Reasoning)
  4. 0.90.9Qwen3.5 4B (Reasoning)
  5. 0.90.9Qwen3 Coder Next
  6. 0.90.9Mistral Small 4 (Non-reasoning)
  7. 11Gemma 4 26B A4B (Non-reasoning)
  8. 11gpt-oss-20b (Low)
  9. 11NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)
  10. 11Ministral 3 14B
Data from Artificial Analysis

Price

$ per 1M tokens (3:1) · #58 of 169
  1. $0.240.24Hy3
  2. $0.240.24gpt-oss-120b (Low)
  3. $0.260.26MiniMax-M3.1-Flash
  4. $0.260.26gpt-oss-120b (High)
  5. $0.260.26Mistral Small 4 (Reasoning)
  6. $0.260.26Mistral Small 4 (Non-reasoning)
  7. $0.280.28Qwen3.5 Omni Flash
  8. $0.280.28Granite 4.2 30B
  9. $0.30.3Llama 4 Scout
  10. $0.30.3NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)
Data from Artificial Analysis

Nearby models

  • Qwen3 Coder NextAlibaba9.2
  • Motif-2-12.7B-ReasoningMotif Technologies9.2
  • Nova PremierAmazon9.2
  • Granite 4.2 3BIBM9.1
  • gpt-oss-20b (High)OpenAI9
  • K2-V2 (Medium)Institute of Foundation Models9
  • Tri-21B-ThinkTrillion Labs9
  • Gemma 4 E4B (Reasoning)Google8.9
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
  • Magistral Small 1.2Mistral8.6
  • Ministral 3 14BMistral6
  • Ministral 3 8BMistral5.5
  • Ministral 3 3BMistral4.8
Data from Artificial Analysis
HorizonVascend IDEOlympusTalosCoursesCommunityBenchmark
DiscordGitHubXLet’s talkLegalPrivacyCookiesData useSecurity
© 2026 Vascend Technologies · VAT IT04911550616
ascend