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

GPT-5.6 Terra (High)

  • OpenAI
  • Proprietary
  • Reasoning

Intelligence

Intelligence Index

#61 of 266
  1. 35.235Agnes 2.5 Pro Beta
  2. 34.835DeepSeek V4 Flash Vision (Max)
  3. 34.635GPT-6 Luna (Xhigh)
  4. 34.535Claude Haiku 5.5 (Medium)
  5. 34.334GLM-5.3 (Low)
  6. 34.234GPT-5.6 Terra (High)
  7. 33.934JT-4.1 Flash 236B A21B (Reasoning)
  8. 33.734Qwen3.8 27B (Xhigh)
  9. 33.634Motif 3
  10. 33.534Gemini 3.8 Flash (Low)
Data from Artificial Analysis

Evaluations

  • AA-Omniscience Accuracy45.5%#40
  • Humanity's Last Exam38.5%#54
  • Terminal-Bench 4.01.5%#72
  • AA-LCR77.7%#72
  • SciCode52.4%#50
  • CritPt22.9%#32
  • MMMU-Pro79.1%#31
  • GPQA Diamond89.6%#28
  • IFBench64.4%#31
  • τ²-Bench Telecom78.4%#43
  • τ²-Bench Banking28.7%#33
  • Terminal-Bench Hard57.6%#2
GPT-5.6 Terra (High)Median
Data from Artificial Analysis

Speed and price

Speed

tokens per second · #68 of 162
  1. 122122Qwen3.5 Omni Plus
  2. 120120GPT-6 Luna (Non-reasoning)
  3. 120120Nova 2.0 Pro Preview (Low)
  4. 120120GPT-6 Luna (High)
  5. 119119Ministral 3 8B
  6. 119119GPT-5.6 Terra (High)
  7. 118118GPT-5.6 Terra (Xhigh)
  8. 118118Llama 4 Scout
  9. 118118Gemma 4 12B (Non-reasoning)
  10. 116116GPT-6 Luna (Low)
Data from Artificial Analysis

Latency

seconds to first token · #86 of 162
  1. 2.12.1Qwen3.6 35B A3B (Reasoning)
  2. 2.12.1Qwen3.8-Flash-Next
  3. 2.22.2Qwen3.5 397B A17B (Non-reasoning)
  4. 2.22.2Qwen3.5 397B A17B (Reasoning)
  5. 2.22.2K2 Horizon 375B A23B
  6. 2.22.2GPT-5.6 Terra (High)
  7. 2.22.2Gemma 4 12B (Reasoning)
  8. 2.32.3Gemma 4 12B (Non-reasoning)
  9. 2.32.3Qwen3.5 122B A10B (Reasoning)
  10. 2.32.3Hermes 4 - Llama-3.1 405B (Non-reasoning)
Data from Artificial Analysis

Price

$ per 1M tokens (3:1) · #147 of 169
  1. $44Claude Sonnet 5.5 (Medium)
  2. $44Claude Sonnet 5.5 (Low)
  3. $4.384.38Command A
  4. $4.54.5GPT-5.6 Terra (Max)
  5. $4.54.5GPT-5.6 Terra (Xhigh)
  6. $4.54.5GPT-5.6 Terra (High)
  7. $4.54.5GPT-5.6 Terra (Medium)
  8. $4.54.5Gemini 3.1 Pro Preview
  9. $4.54.5GPT-5.6 Terra (Low)
  10. $4.54.5GPT-5.6 Terra (Non-reasoning)
Data from Artificial Analysis

Nearby models

  • Agnes 2.5 Pro BetaSapiens AI35.2
  • DeepSeek V4 Flash Vision (Max)DeepSeek34.8
  • GPT-6 Luna (Xhigh)OpenAI34.6
  • Claude Haiku 5.5 (Medium)Anthropic34.5
  • GLM-5.3 (Low)Z AI34.3
  • JT-4.1 Flash 236B A21B (Reasoning)China Mobile33.9
  • Qwen3.8 27B (Xhigh)Alibaba33.7
  • Motif 3Motif Technologies33.6
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