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

Magistral Medium 1.2

  • Mistral
  • Release · September 18, 2025
  • Proprietary
  • Reasoning

Intelligence

Intelligence Index

#146 of 266
  1. 12.513Qwen3.5 Omni Flash
  2. 12.513MiniCPM5-2B
  3. 12.312Mercury 2.5
  4. 12.212JT-MINI
  5. 11.812Nova 2.0 Lite (Low)
  6. 11.812Magistral Medium 1.2
  7. 11.712HyperNova 60B 2605 (High, Based on gpt-oss-120b)
  8. 11.712Nemotron Cascade 2 30B A3B
  9. 11.612gpt-oss-120b (High)
  10. 11.512K2 Think V2
Data from Artificial Analysis

Evaluations

  • AA-Omniscience Accuracy20.8%#112
  • Humanity's Last Exam10.3%#153
  • AA-LCR53%#140
  • CritPt0.3%#117
  • MMMU-Pro59.7%#91
  • GPQA Diamond73.9%#99
  • IFBench43%#78
  • τ²-Bench Telecom52.1%#63
  • τ²-Bench Banking5.6%#84
  • Terminal-Bench Hard12.9%#50
Magistral Medium 1.2Median
Data from Artificial Analysis

Nearby models

  • Qwen3.5 Omni FlashAlibaba12.5
  • MiniCPM5-2BOpenBMB12.5
  • Mercury 2.5Inception12.3
  • JT-MINIChina Mobile12.2
  • Nova 2.0 Lite (Low)Amazon11.8
  • HyperNova 60B 2605 (High, Based on gpt-oss-120b)Multiverse Computing11.7
  • Nemotron Cascade 2 30B A3BNVIDIA11.7
  • gpt-oss-120b (High)OpenAI11.6
Data from Artificial Analysis

Same lab

  • Mistral Large 4 PreviewMistral38.4
  • Mistral Medium 3.5Mistral14.2
  • Mistral Small 4 (Reasoning)Mistral11.3
  • Mistral Small 4 (Non-reasoning)Mistral9
  • 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