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

Grok 4.7 (Xhigh)

  • SpaceXAI
  • Release · September 21, 2026
  • Proprietary
  • Reasoning

Intelligence

Intelligence Index

#25 of 266
  1. 49.650GPT-6 Astra (Medium)
  2. 48.949Claude Fable 5.1 (Medium)
  3. 47.848GPT-6.1 Sol (Medium)
  4. 46.847Claude Sonnet 5.5 (High)
  5. 46.847Claude Fable 5.1 (Low)
  6. 46.446Grok 4.7 (Xhigh)
  7. 46.346MiMo-V2.6-Pro
  8. 46.346Grok 4.7 (High)
  9. 45.846GPT-6 Astra (Low)
  10. 45.445Qwen3.8 Max (0902)
Data from Artificial Analysis

Evaluations

  • AA-Briefcase1,639#7
  • AA-Omniscience Accuracy47.5%#36
  • AA-Omniscience Non-Hallucination70.7%#8
  • AutomationBench-AA65.6%#10
  • GDPval-AA1,714#8
  • Humanity's Last Exam43.1%#38
  • GDP.pdf20%#15
  • Terminal-Bench 4.025.8%#42
  • AA-LCR76.7%#79
  • SciCode57.4%#20
  • CritPt17.7%#45
  • Terminal-Bench-Science4.8%#17
  • FrontierCode33.8%#22
  • AA-AnalystAgent52.5%#6
  • Harvey LAB-AA9.4%#3
  • AA-3D995#10
  • ITBench-AA42.1%#7
  • MLCR-AA20%#10
  • PersonalityBench: Expressiveness72.1#11
  • PersonalityBench: Organization26.4#24
  • PersonalityBench: Transparency64.5#12
  • PersonalityBench: Slop6.1#25
  • PersonalityBench: Informativeness23.8#21
  • PersonalityBench: Warmth39.1#19
  • PersonalityBench: Conviction84.8#4
  • PersonalityBench: Imagination28.9#24
Grok 4.7 (Xhigh)Median
Data from Artificial Analysis

Cost per task

Cost per task

$ per Intelligence Index task · #19 of 24
  1. $1.241.24Gemini 3.8 Flash (High)
  2. $1.991.99Gemini 4 Argon (High)
  3. $2.012.01GLM-5.3 (Max)
  4. $2.112.11Kimi K3.1 Pro
  5. $3.263.26GPT-6 Astra (Max)
  6. $3.743.74Grok 4.7 (Xhigh)
  7. $4.544.54Muse Wonder (Max)
  8. $5.415.41Qwen3.8 Max (0902)
  9. $5.465.46Claude Sonnet 5.5 (Max)
  10. $5.985.98Claude Opus 5.5 (Max)
Data from Artificial Analysis

Time per task

seconds per task · #22 of 26
  1. 723723Gemini 4 Argon (High)
  2. 736736Claude Fable 5.1 (Max)
  3. 791791Claude Opus 5.5 (Max)
  4. 824824GLM-5.3-Flash
  5. 846846Kimi K3.1 Pro
  6. 901901Grok 4.7 (Xhigh)
  7. 936936Claude Sonnet 5.5 (Max)
  8. 1,0131,013MiMo-V2.6-Pro
  9. 1,2001,200Qwen3.8 27B (Xhigh)
  10. 2,0572,057Qwen3.8 Max (0902)
Data from Artificial Analysis

Tokens per task

output tokens per task · #22 of 27
  1. 69.5K70KMistral Large 4 Preview
  2. 71K71KGemini 3.8 Flash (High)
  3. 71.1K71KGLM-5.3 (Max)
  4. 78.1K78KClaude Fable 5.1 (Max)
  5. 78.6K79KMiniMax-M3.1-Flash
  6. 80.6K81KGrok 4.7 (Xhigh)
  7. 89.5K90KDeepSeek V4.1 Flash 1017 (Max)
  8. 107.7K108KQwen3.8 Max (0902)
  9. 119.2K119KClaude Opus 5.5 (Max)
  10. 162.2K162KClaude Haiku 5.5 (Max)
Data from Artificial Analysis

Speed and price

Speed

tokens per second · #96 of 162
  1. 9999GPT-5.3 Codex (Xhigh)
  2. 9898GLM-5.3 (Max)
  3. 9696Qwen3 Omni 30B A3B Instruct
  4. 9696Claude Opus 5.5 (Max)
  5. 9494Qwen3 Coder Next
  6. 9393Grok 4.7 (Xhigh)
  7. 9292GPT-6 Luna (Medium)
  8. 9191GLM-5.3 (Low)
  9. 9191Gemma 4 26B A4B (Reasoning)
  10. 8989Llama 3.3 Instruct 70B
Data from Artificial Analysis

Latency

seconds to first token · #146 of 162
  1. 27.327Gemini 3.8 Flash (High)
  2. 27.327Claude Sonnet 5.5 (Xhigh)
  3. 27.528Muse Wonder (Max)
  4. 30.330Claude Opus 5.5 (High)
  5. 36.136GPT-6.1 Sol (High)
  6. 40.340Grok 4.7 (Xhigh)
  7. 40.741GPT-6 Astra (High)
  8. 54.955GPT-5.3 Codex (Xhigh)
  9. 5757Gemini 4 Argon (High)
  10. 59.560Claude Haiku 5.5 (Xhigh)
Data from Artificial Analysis

Price

$ per 1M tokens (3:1) · #122 of 169
  1. $1.981.98DeepSeek V4 Pro 0813 (Non-reasoning)
  2. $22Muse Spark Open (Xhigh)
  3. $2.072.07Mistral Large 4 Preview
  4. $2.152.15GLM-5.3 (Max)
  5. $2.152.15GLM-5.3 (Low)
  6. $33Grok 4.7 (Xhigh)
  7. $33Grok 4.7 (High)
  8. $33Qwen3.8 Max (0902)
  9. $33Grok 4.7 (Low)
  10. $33Qwen3.8 2.4T A95B
Data from Artificial Analysis

Nearby models

  • GPT-6 Astra (Medium)OpenAI49.6
  • Claude Fable 5.1 (Medium)Anthropic48.9
  • GPT-6.1 Sol (Medium)OpenAI47.8
  • Claude Sonnet 5.5 (High)Anthropic46.8
  • Claude Fable 5.1 (Low)Anthropic46.8
  • MiMo-V2.6-ProXiaomi46.3
  • Grok 4.7 (High)SpaceXAI46.3
  • GPT-6 Astra (Low)OpenAI45.8
Data from Artificial Analysis

Same lab

  • Grok 4.7 (Low)SpaceXAI42.2
Data from Artificial Analysis
HorizonVascend IDEOlympusTalosCoursesCommunityBenchmark
DiscordGitHubXLet’s talkLegalPrivacyCookiesData useSecurity
© 2026 Vascend Technologies · VAT IT04911550616
ascend