Vascend
HorizonVascend IDEVascend CLICommunityBenchmarkContacto
AccederÚnete a Discord
InicioHorizonIDECLIAcceder
ChangelogInteligenciaCoste por tareaCoding Agent IndexCyber IndexDecision IndexBenchmarksVelocidadLatenciaPrecioClasificación
Benchmark

Magistral Small 1.2

  • Mistral
  • Lanzamiento · 17 de septiembre de 2025
  • Pesos abiertos
  • Razonamiento

Inteligencia

Intelligence Index

#189 de 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)
Datos de Artificial Analysis

Evaluaciones

  • 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 1.2Mediana
Datos de Artificial Analysis

Velocidad y precio

Velocidad

tokens por segundo · #112 de 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)
Datos de Artificial Analysis

Latencia

segundos al primer token · #60 de 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)
Datos de Artificial Analysis

Precio

$ por 1M tokens (3:1) · #87 de 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
Datos de Artificial Analysis

Modelos cercanos

  • 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
Datos de Artificial Analysis

Mismo laboratorio

  • 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
Datos de Artificial Analysis
HorizonVascend IDEOlympusTalosCursosCommunityBenchmark
DiscordGitHubXHablemosAvisos legalesPrivacidadCookiesUso de datosSeguridad
© 2026 Vascend Technologies · VAT IT04911550616
ascend