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

Qwen3.8 27B (Medium)

  • Alibaba
  • Open weights
  • Reasoning

Intelligence

Intelligence Index

#76 of 266
  1. 29.930GPT-6 Luna (Medium)
  2. 29.730Gemini 3.1 Pro Preview
  3. 29.530Claude Haiku 5.5 (Low)
  4. 29.229MiniMax-M3
  5. 28.228Nex-N2-Pro (Based on Qwen3.5-397B-A17B)
  6. 27.628Qwen3.8 27B (Medium)
  7. 27.528GPT-5.6 Terra (Low)
  8. 27.327JT-4.1 Flash 236B A21B (Non-reasoning)
  9. 26.727Quasar 438B (Max, Based on GLM-5.2)
  10. 26.627Solar Pro 4
Data from Artificial Analysis

Evaluations

  • AA-Omniscience Accuracy18.4%#133
  • Humanity's Last Exam14.1%#119
  • Terminal-Bench 4.05.1%#64
  • AA-LCR79.7%#51
  • SciCode39%#109
  • CritPt0%#143
  • MMMU-Pro74.2%#52
  • GPQA Diamond84.6%#51
  • τ²-Bench Banking47.4%#5
Qwen3.8 27B (Medium)Median
Data from Artificial Analysis

Speed and price

Speed

tokens per second · #147 of 162
  1. 5252Qwen3.8-Flash-Next
  2. 5151Granite 4.2 3B
  3. 5151GPT-6.1 Sol (Medium)
  4. 5050Qwen3.8 27B (Non-reasoning)
  5. 4949Qwen3.8 27B (Low)
  6. 4848Qwen3.8 27B (Medium)
  7. 4848Granite 4.2 30B
  8. 4646Phi-4 Mini Instruct
  9. 4545Gemma 4 E4B (Reasoning)
  10. 4545Qwen3.8 27B (Xhigh)
Data from Artificial Analysis

Latency

seconds to first token · #117 of 162
  1. 3.73.7Ring-2.6-1T
  2. 3.83.8MiMo-V2.6-Flash
  3. 3.93.9Qwen3.8 27B (Xhigh)
  4. 3.93.9Qwen3.8 27B (Low)
  5. 44Qwen3.8 27B (Non-reasoning)
  6. 44Qwen3.8 27B (Medium)
  7. 44GPT-6.1 Sol (Medium)
  8. 5.15.1GPT-6 Astra (Medium)
  9. 5.25.2Claude Fable 5.1 (Medium)
  10. 6.26.2Claude Opus 5.5 (Low)
Data from Artificial Analysis

Price

$ per 1M tokens (3:1) · #100 of 169
  1. $0.850.85Nova 2.0 Lite (Non-reasoning)
  2. $0.980.98Apodex 1.1
  3. $1.11.1Qwen3.5 122B A10B (Non-reasoning)
  4. $1.11.1Qwen3.5 122B A10B (Reasoning)
  5. $1.131.13Qwen3.8 27B (Xhigh)
  6. $1.131.13Qwen3.8 27B (Medium)
  7. $1.131.13Qwen3.8 27B (Low)
  8. $1.131.13Nemotron 3 Ultra 550B A55B (Reasoning)
  9. $1.131.13Qwen3.8 27B (Non-reasoning)
  10. $1.31.3LongCat 2.0
Data from Artificial Analysis

Nearby models

  • GPT-6 Luna (Medium)OpenAI29.9
  • Gemini 3.1 Pro PreviewGoogle29.7
  • Claude Haiku 5.5 (Low)Anthropic29.5
  • MiniMax-M3MiniMax29.2
  • Nex-N2-Pro (Based on Qwen3.5-397B-A17B)Nex AGI28.2
  • GPT-5.6 Terra (Low)OpenAI27.5
  • JT-4.1 Flash 236B A21B (Non-reasoning)China Mobile27.3
  • Quasar 438B (Max, Based on GLM-5.2)Multiverse Computing26.7
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 (Low)Alibaba26.2
  • 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