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

GPT-5.3 Codex (Xhigh)

  • OpenAI
  • Veröffentlichung · 5. Februar 2026
  • Proprietär
  • Reasoning

Intelligenz

Intelligence Index

#67 von 266
  1. 33,934JT-4.1 Flash 236B A21B (Reasoning)
  2. 33,734Qwen3.8 27B (Xhigh)
  3. 33,634Motif 3
  4. 33,534Gemini 3.8 Flash (Low)
  5. 32,933GPT-6 Luna (High)
  6. 32,533GPT-5.3 Codex (Xhigh)
  7. 30,531K2 Horizon 375B A23B
  8. 30,330Beam 1.0
  9. 30,130GPT-5.6 Terra (Medium)
  10. 29,930GPT-6 Luna (Medium)
Daten von Artificial Analysis

Bewertungen

  • AA-Omniscience Accuracy52,9%#27
  • Humanity's Last Exam42,5%#42
  • AA-LCR83,3%#13
  • CritPt16,9%#51
  • MMMU-Pro78,5%#36
  • GPQA Diamond91,5%#19
  • IFBench75,4%#11
  • τ²-Bench Telecom86%#24
  • Terminal-Bench Hard53%#5
GPT-5.3 Codex (Xhigh)Median
Daten von Artificial Analysis

Geschwindigkeit und Preis

Geschwindigkeit

Tokens pro Sekunde · #91 von 162
  1. 105105Muse Glimmer (High)
  2. 105105DeepSeek V4 Pro 0813 (Max)
  3. 103103MiniMax-M3
  4. 103103Qwen3 Omni 30B A3B (Reasoning)
  5. 100100DeepSeek V4 Pro 0813 (Non-reasoning)
  6. 9999GPT-5.3 Codex (Xhigh)
  7. 9898GLM-5.3 (Max)
  8. 9696Qwen3 Omni 30B A3B Instruct
  9. 9696Claude Opus 5.5 (Max)
  10. 9494Qwen3 Coder Next
Daten von Artificial Analysis

Latenz

Sekunden bis zum ersten Token · #148 von 162
  1. 27,528Muse Wonder (Max)
  2. 30,330Claude Opus 5.5 (High)
  3. 36,136GPT-6.1 Sol (High)
  4. 40,340Grok 4.7 (Xhigh)
  5. 40,741GPT-6 Astra (High)
  6. 54,955GPT-5.3 Codex (Xhigh)
  7. 5757Gemini 4 Argon (High)
  8. 59,560Claude Haiku 5.5 (Xhigh)
  9. 74,575Claude Fable 5.1 (Xhigh)
  10. 78,579GPT-6 Luna (Max)
Daten von Artificial Analysis

Preis

$ pro 1M Tokens (3:1) · #152 von 169
  1. $4,54,5GPT-5.6 Terra (High)
  2. $4,54,5GPT-5.6 Terra (Medium)
  3. $4,54,5Gemini 3.1 Pro Preview
  4. $4,54,5GPT-5.6 Terra (Low)
  5. $4,54,5GPT-5.6 Terra (Non-reasoning)
  6. $4,814,81GPT-5.3 Codex (Xhigh)
  7. $88Claude Opus 5.5 (Max)
  8. $88Claude Opus 5.5 (Xhigh)
  9. $88Claude Opus 5.5 (High)
  10. $88Muse Wonder (Max)
Daten von Artificial Analysis

Ähnliche Modelle

  • JT-4.1 Flash 236B A21B (Reasoning)China Mobile33,9
  • Qwen3.8 27B (Xhigh)Alibaba33,7
  • Motif 3Motif Technologies33,6
  • Gemini 3.8 Flash (Low)Google33,5
  • GPT-6 Luna (High)OpenAI32,9
  • K2 Horizon 375B A23BInstitute of Foundation Models30,5
  • Beam 1.0Reflection30,3
  • GPT-5.6 Terra (Medium)OpenAI30,1
Daten von Artificial Analysis

Gleiches Labor

  • GPT-6 Astra (Max)OpenAI52,7
  • GPT-6 Astra (Xhigh)OpenAI52,4
  • GPT-6.1 Sol (Max)OpenAI51,8
  • GPT-6.1 Sol (Xhigh)OpenAI51
  • GPT-6 Astra (High)OpenAI50,9
  • GPT-6.1 Sol (High)OpenAI50,2
  • GPT-6 Astra (Medium)OpenAI49,6
  • GPT-6.1 Sol (Medium)OpenAI47,8
Daten von Artificial Analysis
HorizonVascend IDEOlympusTalosKurseCommunityBenchmark
DiscordGitHubXKontaktRechtlichesDatenschutzCookiesDatennutzungSicherheit
© 2026 Vascend Technologies · VAT IT04911550616
ascend