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

GPT-5.3 Codex (Xhigh)

  • OpenAI
  • Release · February 5, 2026
  • Proprietary
  • Reasoning

Intelligence

Intelligence Index

#67 of 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)
Data from Artificial Analysis

Evaluations

  • 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
Data from Artificial Analysis

Speed and price

Speed

tokens per second · #91 of 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
Data from Artificial Analysis

Latency

seconds to first token · #148 of 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)
Data from Artificial Analysis

Price

$ per 1M tokens (3:1) · #152 of 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)
Data from Artificial Analysis

Nearby models

  • 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
Data from Artificial Analysis

Same lab

  • 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
Data from Artificial Analysis
HorizonVascend IDEOlympusTalosCoursesCommunityBenchmark
DiscordGitHubXLet’s talkLegalPrivacyCookiesData useSecurity
© 2026 Vascend Technologies · VAT IT04911550616
ascend