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

Qwen3.8 27B (Low)

  • Alibaba
  • Open weights
  • Reasoning

Intelligence

Intelligence Index

#83 of 266
  1. 27.327JT-4.1 Flash 236B A21B (Non-reasoning)
  2. 26.727Quasar 438B (Max, Based on GLM-5.2)
  3. 26.627Solar Pro 4
  4. 26.527Nemotron 3.5 Super VL
  5. 26.426Apodex 1.1
  6. 26.226Qwen3.8 27B (Low)
  7. 2626GPT-5.5 Instant (June 2026)
  8. 25.826Kimi K2.7 Code
  9. 25.726Inkling Small
  10. 25.325Hy3
Data from Artificial Analysis

Evaluations

  • AA-Omniscience Accuracy17.1%#148
  • Humanity's Last Exam14%#121
  • Terminal-Bench 4.02.5%#69
  • AA-LCR77.3%#73
  • SciCode40.1%#103
  • CritPt0%#143
  • MMMU-Pro73.8%#54
  • GPQA Diamond84.6%#51
  • τ²-Bench Banking32.2%#28
Qwen3.8 27B (Low)Median
Data from Artificial Analysis

Speed and price

Speed

tokens per second · #146 of 162
  1. 5252Llama 4 Maverick
  2. 5252Qwen3.8-Flash-Next
  3. 5151Granite 4.2 3B
  4. 5151GPT-6.1 Sol (Medium)
  5. 5050Qwen3.8 27B (Non-reasoning)
  6. 4949Qwen3.8 27B (Low)
  7. 4848Qwen3.8 27B (Medium)
  8. 4848Granite 4.2 30B
  9. 4646Phi-4 Mini Instruct
  10. 4545Gemma 4 E4B (Reasoning)
Data from Artificial Analysis

Latency

seconds to first token · #115 of 162
  1. 3.53.5Apertus 8B Instruct
  2. 3.63.6Mercury 2.5
  3. 3.73.7Ring-2.6-1T
  4. 3.83.8MiMo-V2.6-Flash
  5. 3.93.9Qwen3.8 27B (Xhigh)
  6. 3.93.9Qwen3.8 27B (Low)
  7. 44Qwen3.8 27B (Non-reasoning)
  8. 44Qwen3.8 27B (Medium)
  9. 44GPT-6.1 Sol (Medium)
  10. 5.15.1GPT-6 Astra (Medium)
Data from Artificial Analysis

Price

$ per 1M tokens (3:1) · #101 of 169
  1. $0.980.98Apodex 1.1
  2. $1.11.1Qwen3.5 122B A10B (Non-reasoning)
  3. $1.11.1Qwen3.5 122B A10B (Reasoning)
  4. $1.131.13Qwen3.8 27B (Xhigh)
  5. $1.131.13Qwen3.8 27B (Medium)
  6. $1.131.13Qwen3.8 27B (Low)
  7. $1.131.13Nemotron 3 Ultra 550B A55B (Reasoning)
  8. $1.131.13Qwen3.8 27B (Non-reasoning)
  9. $1.31.3LongCat 2.0
  10. $1.351.35Qwen3.5 397B A17B (Non-reasoning)
Data from Artificial Analysis

Nearby models

  • JT-4.1 Flash 236B A21B (Non-reasoning)China Mobile27.3
  • Quasar 438B (Max, Based on GLM-5.2)Multiverse Computing26.7
  • Solar Pro 4Upstage26.6
  • Nemotron 3.5 Super VLNVIDIA26.5
  • Apodex 1.1Apodex26.4
  • GPT-5.5 Instant (June 2026)OpenAI26
  • Kimi K2.7 CodeKimi25.8
  • Inkling SmallThinking Machines25.7
Data from Artificial Analysis

Same lab

  • Qwen3.8 Max (0902)Alibaba45.4
  • Qwen3.8 2.4T A95BAlibaba39.9
  • Qwen3.8-Flash-NextAlibaba39.8
  • Qwen3.8 27B (Xhigh)Alibaba33.7
  • Qwen3.8 27B (Medium)Alibaba27.6
  • Qwen3.7 PlusAlibaba25.2
  • Qwen3.5 397B A17B (Non-reasoning)Alibaba21.4
  • Qwen3.5 Omni PlusAlibaba20.4
Data from Artificial Analysis
HorizonVascend IDEOlympusTalosCoursesCommunityBenchmark
DiscordGitHubXLet’s talkLegalPrivacyCookiesData useSecurity
© 2026 Vascend Technologies · VAT IT04911550616
ascend