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

Magistral Small 1.2

  • Mistral
  • Release · September 17, 2025
  • Open weights
  • Reasoning

Intelligence

Intelligence Index

#189 of 266
  1. 8.98.9NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)
  2. 8.88.8MiniCPM5-1B (Reasoning)
  3. 8.88.8Sarvam 105B (High)
  4. 8.78.7MiniCPM5-1B (Non-reasoning)
  5. 8.78.7Nova 2.0 Lite (Non-reasoning)
  6. 8.68.6Magistral Small 1.2
  7. 8.48.4Nanbeige4.1-3B
  8. 8.48.4LFM2.5-2.6B
  9. 8.28.2EXAONE 4.0 32B (Reasoning)
  10. 8.28.2Nova 2.0 Omni (Non-reasoning)
Data from Artificial Analysis

Evaluations

  • AA-Omniscience Accuracy13.5%#194
  • Humanity's Last Exam6.4%#181
  • AA-LCR19.3%#197
  • CritPt0.3%#117
  • MMMU-Pro55.5%#94
  • GPQA Diamond66.3%#129
  • IFBench44.4%#72
  • τ²-Bench Telecom27.8%#83
  • τ²-Bench Banking4.5%#92
  • Terminal-Bench Hard4.6%#81
Magistral Small 1.2Median
Data from Artificial Analysis

Speed and price

Speed

tokens per second · #112 of 162
  1. 8181Hy3
  2. 8080Claude Opus 5.5 (High)
  3. 8080Qwen3.5 9B (Non-reasoning)
  4. 7878Grok 4.7 (Low)
  5. 7777Ministral 3 14B
  6. 7777Magistral Small 1.2
  7. 7676LongCat 2.0
  8. 7070GLM-5.3-Flash
  9. 7070Claude Fable 5.1 (Max)
  10. 6666GPT-6 Astra (Max)
Data from Artificial Analysis

Latency

seconds to first token · #60 of 162
  1. 1.41.4Claude Sonnet 5.5 (Medium)
  2. 1.41.4GPT-5.6 Terra (Low)
  3. 1.41.4Agnes 2.5 Pro Beta
  4. 1.41.4Reka Flash 3
  5. 1.51.5GPT-5.6 Terra (Medium)
  6. 1.51.5Magistral Small 1.2
  7. 1.61.6DeepSeek V4 Flash Vision (Max)
  8. 1.61.6Inkling Small
  9. 1.61.6Sarvam 105B (High)
  10. 1.71.7Claude Fable 5.1 (Low)
Data from Artificial Analysis

Price

$ per 1M tokens (3:1) · #87 of 169
  1. $0.60.6Beam 1.0
  2. $0.640.64Nemotron 3 Nano Omni 30B A3B Reasoning
  3. $0.660.66DeepSeek V4 Flash Vision (Max)
  4. $0.670.67Llama 3.3 Instruct 70B
  5. $0.70.7Qwen3.7 Plus
  6. $0.750.75Magistral Small 1.2
  7. $0.840.84Qwen3.6 35B A3B (Reasoning)
  8. $0.840.84Qwen3.6 35B A3B (Non-reasoning)
  9. $0.850.85Gemini 3.5 Flash-Lite
  10. $0.850.85Ring-2.6-1T
Data from Artificial Analysis

Nearby models

  • NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)NVIDIA8.9
  • MiniCPM5-1B (Reasoning)OpenBMB8.8
  • Sarvam 105B (High)Sarvam8.8
  • MiniCPM5-1B (Non-reasoning)OpenBMB8.7
  • Nova 2.0 Lite (Non-reasoning)Amazon8.7
  • Nanbeige4.1-3BNanbeige8.4
  • LFM2.5-2.6BLiquid AI8.4
  • EXAONE 4.0 32B (Reasoning)LG AI Research8.2
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
  • 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