Vascend
Sign inJoin Discord
Benchmark

GPT-6.1 Terra (Xhigh)

  • OpenAI
  • Release · October 26, 2026
  • Proprietary
  • Reasoning

Intelligence

Intelligence Index

#23 of 77
  1. 4949Claude Fable 5.1 (Max)
  2. 48.148Claude Opus 5.5 (Medium)
  3. 4747Claude Fable 5.1 (High)
  4. 46.146GPT-6.1 Sol (Medium)
  5. 4646Kimi K3.1 Pro
  6. 4545GPT-6.1 Terra (Xhigh)
  7. 43.343Muse Wonder (Max)
  8. 4343GPT-6 Astra (Low)
  9. 4343Claude Fable 5.1 (Medium)
  10. 42.342GPT-6.1 Terra (High)
Data from Artificial Analysis

Evaluations

  • AA-Briefcase v1.11,333#52
  • AA-Omniscience v1.1 Accuracy48%#30
  • AA-Omniscience v1.1 Non-Hallucination63.3%#23
  • AutomationBench-AA59.9%#31
  • Terminal-Bench-Science 0.141.9%#18
  • FrontierCode 2.036.9%#13
  • HLE-Diamond42.3%#24
  • GDP.pdf26.6%#22
  • Terminal-Bench 4.046.5%#24
  • CritPt v2 (Hard Subset)57.5%#18
  • GDPval-AA v2.11,415#52
  • MMMU-Pro83.8%#20
  • FrontierCode 1.141.4%#30
  • AA-LCR v1.181.7%#34
  • SciCode53.4%#46
  • Humanity's Last Exam43.7%#37
  • CritPt26.6%#26
GPT-6.1 Terra (Xhigh)Median
Data from Artificial Analysis

Speed and price

Speed

tokens per second · #94 of 161
  1. 9191GPT-6.1 Terra (Non-reasoning)
  2. 9191GPT-6.1 Terra (Low)
  3. 9191GPT-6.1 Terra (Medium)
  4. 9191GPT-6.1 Terra (Max)
  5. 9191GPT-6.1 Terra (High)
  6. 9191GPT-6.1 Terra (Xhigh)
  7. 9090Reka Flash 3
  8. 8989Llama 3.3 Instruct 70B
  9. 8888Grok 4.7 (Low)
  10. 8787GLM-5.3 (Low)
Data from Artificial Analysis

Latency

seconds to first token · #138 of 161
  1. 15.415Claude Opus 5.5 (Medium)
  2. 16.416GPT-6 Luna (Xhigh)
  3. 17.918Claude Haiku 5.5 (High)
  4. 2020Gemini 3.1 Pro Preview
  5. 21.321Grok 4.7 (High)
  6. 23.724GPT-6.1 Terra (Xhigh)
  7. 25.125Muse Wonder (Max)
  8. 27.528Gemini 3.8 Flash (High)
  9. 27.928Claude Sonnet 5.5 (Xhigh)
  10. 35.135Claude Opus 5.5 (High)
Data from Artificial Analysis

Price

$ per 1M tokens (3:1) · #118 of 169
  1. $1.711.71Kimi K2.7 Code
  2. $1.761.76Inkling (Xhigh)
  3. $1.981.98DeepSeek V4 Pro 0813 (Max)
  4. $1.981.98DeepSeek V4 Pro 0813 (Non-reasoning)
  5. $22GPT-6.1 Terra (Max)
  6. $22GPT-6.1 Terra (Xhigh)
  7. $22GPT-6.1 Terra (High)
  8. $22GPT-6.1 Terra (Medium)
  9. $22GPT-6.1 Terra (Non-reasoning)
  10. $22GPT-6.1 Terra (Low)
Data from Artificial Analysis

Nearby models

Data from Artificial Analysis

Same lab

Data from Artificial Analysis