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

GLM-5.3 (Low)

  • Z AI
  • Open weights
  • Reasoning

Intelligence

Intelligence Index

#60 of 266
  1. 35.936Claude Sonnet 5.5 (Low)
  2. 35.235Agnes 2.5 Pro Beta
  3. 34.835DeepSeek V4 Flash Vision (Max)
  4. 34.635GPT-6 Luna (Xhigh)
  5. 34.535Claude Haiku 5.5 (Medium)
  6. 34.334GLM-5.3 (Low)
  7. 34.234GPT-5.6 Terra (High)
  8. 33.934JT-4.1 Flash 236B A21B (Reasoning)
  9. 33.734Qwen3.8 27B (Xhigh)
  10. 33.634Motif 3
Data from Artificial Analysis

Evaluations

  • AA-Omniscience Accuracy33.9%#67
  • Humanity's Last Exam36.6%#61
  • Terminal-Bench 4.034.9%#29
  • AA-LCR72.7%#94
  • SciCode42%#96
  • CritPt14.6%#57
GLM-5.3 (Low)Median
Data from Artificial Analysis

Speed and price

Speed

tokens per second · #98 of 162
  1. 9696Qwen3 Omni 30B A3B Instruct
  2. 9696Claude Opus 5.5 (Max)
  3. 9494Qwen3 Coder Next
  4. 9393Grok 4.7 (Xhigh)
  5. 9292GPT-6 Luna (Medium)
  6. 9191GLM-5.3 (Low)
  7. 9191Gemma 4 26B A4B (Reasoning)
  8. 8989Llama 3.3 Instruct 70B
  9. 8888Reka Flash 3
  10. 8686Grok 4.7 (High)
Data from Artificial Analysis

Latency

seconds to first token · #107 of 162
  1. 2.82.8GPT-6 Luna (Medium)
  2. 2.82.8Kimi K2.7 Code
  3. 2.82.8Qwen3.8 Max (0902)
  4. 2.82.8GLM-5.3-Flash
  5. 2.92.9Qwen3.8 2.4T A95B
  6. 33GLM-5.3 (Low)
  7. 3.13.1Kimi K3.1 Pro
  8. 3.13.1MiMo-V2.6-Pro
  9. 3.53.5Apertus 8B Instruct
  10. 3.63.6Mercury 2.5
Data from Artificial Analysis

Price

$ per 1M tokens (3:1) · #121 of 169
  1. $1.981.98DeepSeek V4 Pro 0813 (Max)
  2. $1.981.98DeepSeek V4 Pro 0813 (Non-reasoning)
  3. $22Muse Spark Open (Xhigh)
  4. $2.072.07Mistral Large 4 Preview
  5. $2.152.15GLM-5.3 (Max)
  6. $2.152.15GLM-5.3 (Low)
  7. $33Grok 4.7 (Xhigh)
  8. $33Grok 4.7 (High)
  9. $33Qwen3.8 Max (0902)
  10. $33Grok 4.7 (Low)
Data from Artificial Analysis

Nearby models

  • Claude Sonnet 5.5 (Low)Anthropic35.9
  • 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
  • GPT-5.6 Terra (High)OpenAI34.2
  • JT-4.1 Flash 236B A21B (Reasoning)China Mobile33.9
  • Qwen3.8 27B (Xhigh)Alibaba33.7
Data from Artificial Analysis

Same lab

  • GLM-5.3 (Max)Z AI44.8
  • GLM-5.3-FlashZ AI41.8
Data from Artificial Analysis
HorizonVascend IDEOlympusTalosCoursesCommunityBenchmark
DiscordGitHubXLet’s talkLegalPrivacyCookiesData useSecurity
© 2026 Vascend Technologies · VAT IT04911550616
ascend