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

Gemini 4 Argon (High)

  • Google
  • Release · September 30, 2026
  • Proprietary
  • Reasoning

Intelligence

Intelligence Index

#10 of 266
  1. 55.155Kimi K3.1 Pro
  2. 53.654Claude Opus 5.5 (High)
  3. 53.453Claude Fable 5.1 (Max)
  4. 53.253Claude Fable 5.1 (Xhigh)
  5. 52.753GPT-6 Astra (Max)
  6. 52.653Gemini 4 Argon (High)
  7. 52.452GPT-6 Astra (Xhigh)
  8. 52.452Muse Wonder (Max)
  9. 51.952Claude Sonnet 5.5 (Xhigh)
  10. 51.852GPT-6.1 Sol (Max)
Data from Artificial Analysis

Evaluations

  • AA-Briefcase1,486#15
  • AA-Omniscience Accuracy49.9%#31
  • AA-Omniscience Non-Hallucination84.9%#1
  • AutomationBench-AA77.5%#1
  • GDPval-AA1,624#13
  • Humanity's Last Exam57.1%#5
  • GDP.pdf21.8%#11
  • Terminal-Bench 4.057.1%#7
  • AA-LCR79.7%#51
  • SciCode61.8%#5
  • CritPt27.1%#23
  • Terminal-Bench-Science52.9%#5
  • FrontierCode43.5%#11
  • AA-AnalystAgent48.8%#9
  • Harvey LAB-AA3.9%#8
  • AA-3D1,153#4
  • MLCR-AA13.9%#17
  • PersonalityBench: Expressiveness82.2#7
  • PersonalityBench: Organization51.8#18
  • PersonalityBench: Transparency16.2#25
  • PersonalityBench: Slop69.5#6
  • PersonalityBench: Informativeness79.7#8
  • PersonalityBench: Warmth74.6#8
  • PersonalityBench: Conviction59.4#13
  • PersonalityBench: Imagination44.2#19
Gemini 4 Argon (High)Median
Data from Artificial Analysis

Cost per task

Cost per task

$ per Intelligence Index task · #15 of 24
  1. $0.840.84Muse Spark Open (Xhigh)
  2. $1.011.01Qwen3.8 27B (Xhigh)
  3. $1.031.03Step 5 Preview
  4. $1.131.13Mistral Large 4 Preview
  5. $1.241.24Gemini 3.8 Flash (High)
  6. $1.991.99Gemini 4 Argon (High)
  7. $2.012.01GLM-5.3 (Max)
  8. $2.112.11Kimi K3.1 Pro
  9. $3.263.26GPT-6 Astra (Max)
  10. $3.743.74Grok 4.7 (Xhigh)
Data from Artificial Analysis

Time per task

seconds per task · #17 of 26
  1. 498498Gemini 3.8 Flash (High)
  2. 507507MiniMax-M3.1-Flash
  3. 578578Mistral Large 4 Preview
  4. 604604GLM-5.3 (Max)
  5. 628628GPT-6.1 Sol (Max)
  6. 723723Gemini 4 Argon (High)
  7. 736736Claude Fable 5.1 (Max)
  8. 791791Claude Opus 5.5 (Max)
  9. 824824GLM-5.3-Flash
  10. 846846Kimi K3.1 Pro
Data from Artificial Analysis

Tokens per task

output tokens per task · #12 of 27
  1. 50K50KGPT-6 Luna (Max)
  2. 51.5K52KK2 Horizon 375B A23B
  3. 53.8K54KMuse Wonder Full (Max)
  4. 54.5K55KMuse Wonder (Max)
  5. 55.2K55KKimi K3.1 Pro
  6. 61.6K62KGemini 4 Argon (High)
  7. 64.1K64KStep 5 Preview
  8. 64.3K64KMiMo-V2.6-Pro
  9. 66.8K67KQwen3.8 27B (Xhigh)
  10. 68.7K69KGLM-5.3-Flash
Data from Artificial Analysis

Speed and price

Speed

tokens per second · #106 of 162
  1. 8888Reka Flash 3
  2. 8686Grok 4.7 (High)
  3. 8383Claude Opus 5.5 (Medium)
  4. 8282Claude Opus 5.5 (Xhigh)
  5. 8282Claude Opus 5.5 (Low)
  6. 8181Gemini 4 Argon (High)
  7. 8181Hy3
  8. 8080Claude Opus 5.5 (High)
  9. 8080Qwen3.5 9B (Non-reasoning)
  10. 7878Grok 4.7 (Low)
Data from Artificial Analysis

Latency

seconds to first token · #149 of 162
  1. 30.330Claude Opus 5.5 (High)
  2. 36.136GPT-6.1 Sol (High)
  3. 40.340Grok 4.7 (Xhigh)
  4. 40.741GPT-6 Astra (High)
  5. 54.955GPT-5.3 Codex (Xhigh)
  6. 5757Gemini 4 Argon (High)
  7. 59.560Claude Haiku 5.5 (Xhigh)
  8. 74.575Claude Fable 5.1 (Xhigh)
  9. 78.579GPT-6 Luna (Max)
  10. 102.7103GPT-5.6 Terra (Max)
Data from Artificial Analysis

Price

$ per 1M tokens (3:1) · #134 of 169
  1. $3.443.44Nova 2.0 Pro Preview (Low)
  2. $3.443.44Nova 2.0 Pro Preview (Non-reasoning)
  3. $3.53.5o3
  4. $44Claude Sonnet 5.5 (Max)
  5. $44Kimi K3.1 Pro
  6. $44Gemini 4 Argon (High)
  7. $44Claude Sonnet 5.5 (Xhigh)
  8. $44GPT-6.1 Sol (Max)
  9. $44GPT-6.1 Sol (Xhigh)
  10. $44GPT-6.1 Sol (High)
Data from Artificial Analysis

Nearby models

  • Kimi K3.1 ProKimi55.1
  • Claude Opus 5.5 (High)Anthropic53.6
  • Claude Fable 5.1 (Max)Anthropic53.4
  • Claude Fable 5.1 (Xhigh)Anthropic53.2
  • GPT-6 Astra (Max)OpenAI52.7
  • GPT-6 Astra (Xhigh)OpenAI52.4
  • Muse Wonder (Max)Meta52.4
  • Claude Sonnet 5.5 (Xhigh)Anthropic51.9
Data from Artificial Analysis

Same lab

  • Gemini 3.8 Flash (High)Google40.9
  • Gemini 3.8 Flash (Medium)Google39.8
  • Gemini 3.8 Flash (Low)Google33.5
  • Gemini 3.1 Pro PreviewGoogle29.7
  • Gemini 3.5 Flash-LiteGoogle22.2
  • Gemma 4 26B A4B (Reasoning)Google16.7
  • Gemma 4 31B (Reasoning)Google14.7
  • Gemma 4 12B (Reasoning)Google14.2
Data from Artificial Analysis
HorizonVascend IDEOlympusTalosCoursesCommunityBenchmark
DiscordGitHubXLet’s talkLegalPrivacyCookiesData useSecurity
© 2026 Vascend Technologies · VAT IT04911550616
ascend