Vascend
HorizonVascend IDEVascend CLICommunityBenchmarkKontakt
AnmeldenDiscord beitreten
StartHorizonIDECLIAnmelden
ChangelogIntelligenzKosten pro AufgabeCoding Agent IndexCyber IndexDecision IndexBenchmarksGeschwindigkeitLatenzPreisRangliste
Benchmark

ERNIE 5.0 Thinking Preview

  • Baidu
  • Veröffentlichung · 13. November 2025
  • Proprietär
  • Reasoning

Intelligenz

Intelligence Index

#124 von 266
  1. 16,617Ring-2.6-1T
  2. 15,616K2 Horizon 3.7B
  3. 15,616Qwen3.5 122B A10B (Reasoning)
  4. 15,215Qwen3.6 35B A3B (Non-reasoning)
  5. 14,715Gemma 4 31B (Reasoning)
  6. 14,314ERNIE 5.0 Thinking Preview
  7. 14,214Nova 2.0 Pro Preview (Medium)
  8. 14,214Mistral Medium 3.5
  9. 14,214Gemma 4 12B (Reasoning)
  10. 13,914Gemma 4 31B (Non-reasoning)
Daten von Artificial Analysis

Bewertungen

  • AA-Omniscience Accuracy22,1%#105
  • Humanity's Last Exam13,3%#125
  • CritPt1,4%#99
  • MMMU-Pro64,6%#76
  • GPQA Diamond77,7%#78
  • IFBench41,4%#83
  • τ²-Bench Telecom83,9%#29
  • Terminal-Bench Hard25%#26
ERNIE 5.0 Thinking PreviewMedian
Daten von Artificial Analysis

Ähnliche Modelle

  • Ring-2.6-1TInclusionAI16,6
  • K2 Horizon 3.7BInstitute of Foundation Models15,6
  • Qwen3.5 122B A10B (Reasoning)Alibaba15,6
  • Qwen3.6 35B A3B (Non-reasoning)Alibaba15,2
  • Gemma 4 31B (Reasoning)Google14,7
  • Nova 2.0 Pro Preview (Medium)Amazon14,2
  • Mistral Medium 3.5Mistral14,2
  • Gemma 4 12B (Reasoning)Google14,2
Daten von Artificial Analysis

Gleiches Labor

  • ERNIE 4.5 300B A47BBaidu7,5
Daten von Artificial Analysis
HorizonVascend IDEOlympusTalosKurseCommunityBenchmark
DiscordGitHubXKontaktRechtlichesDatenschutzCookiesDatennutzungSicherheit
© 2026 Vascend Technologies · VAT IT04911550616
ascend