Vascend
Sign inJoin Discord
Benchmark

GPT-6.1 Terra (Medium)

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

Intelligence

Intelligence Index

#30 of 77
  1. 4343GPT-6 Astra (Low)
  2. 4343Claude Fable 5.1 (Medium)
  3. 42.342GPT-6.1 Terra (High)
  4. 41.141Claude Sonnet 5.5 (High)
  5. 38.539Claude Fable 5.1 (Low)
  6. 38.138GPT-6.1 Terra (Medium)
  7. 36.236Claude Haiku 5.5 (Max)
  8. 3535Grok 4.7 (High)
  9. 34.535GPT-6.1 Sol (Low)
  10. 34.535Claude Opus 5.5 (Low)
Data from Artificial Analysis

Evaluations

  • AA-Briefcase v1.11,191#64
  • AA-Omniscience v1.1 Accuracy47.4%#32
  • AA-Omniscience v1.1 Non-Hallucination60.4%#30
  • AutomationBench-AA57.8%#39
  • Terminal-Bench-Science 0.124.8%#29
  • FrontierCode 2.034.5%#20
  • HLE-Diamond31.3%#34
  • GDP.pdf28.4%#15
  • Terminal-Bench 4.032.3%#40
  • CritPt v2 (Hard Subset)56%#21
  • GDPval-AA v2.11,325#65
  • MMMU-Pro82.8%#23
  • FrontierCode 1.143.7%#19
  • AA-LCR v1.180.7%#40
  • SciCode51.6%#57
  • Humanity's Last Exam40.2%#51
  • CritPt21.4%#38
GPT-6.1 Terra (Medium)Median
Data from Artificial Analysis

Speed and price

Speed

tokens per second · #91 of 161
  1. 9797Gemma 4 26B A4B (Reasoning)
  2. 9797Qwen3 Omni 30B A3B Instruct
  3. 9292Ministral 3 8B
  4. 9191GPT-6.1 Terra (Non-reasoning)
  5. 9191GPT-6.1 Terra (Low)
  6. 9191GPT-6.1 Terra (Medium)
  7. 9191GPT-6.1 Terra (Max)
  8. 9191GPT-6.1 Terra (High)
  9. 9191GPT-6.1 Terra (Xhigh)
  10. 9090Reka Flash 3
Data from Artificial Analysis

Latency

seconds to first token · #75 of 161
  1. 1.91.9Qwen3 Omni 30B A3B (Reasoning)
  2. 1.91.9Qwen3.5 9B (Reasoning)
  3. 1.91.9Llama 3.3 Instruct 70B
  4. 1.91.9Qwen3 Omni 30B A3B Instruct
  5. 22Qwen3.6 35B A3B (Non-reasoning)
  6. 22GPT-6.1 Terra (Medium)
  7. 22Qwen3.8-Flash-Next
  8. 2.12.1Qwen3.5 Omni Plus
  9. 2.12.1Qwen3.6 35B A3B (Reasoning)
  10. 2.12.1Gemma 4 12B (Non-reasoning)
Data from Artificial Analysis

Price

$ per 1M tokens (3:1) · #120 of 169
  1. $1.981.98DeepSeek V4 Pro 0813 (Max)
  2. $1.981.98DeepSeek V4 Pro 0813 (Non-reasoning)
  3. $22GPT-6.1 Terra (Max)
  4. $22GPT-6.1 Terra (Xhigh)
  5. $22GPT-6.1 Terra (High)
  6. $22GPT-6.1 Terra (Medium)
  7. $22GPT-6.1 Terra (Non-reasoning)
  8. $22GPT-6.1 Terra (Low)
  9. $22Muse Spark Open (Xhigh)
  10. $2.072.07Mistral Large 4 Preview
Data from Artificial Analysis

Nearby models

Data from Artificial Analysis

Same lab

Data from Artificial Analysis