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

Qwen3.5 122B A10B (Reasoning)

  • Alibaba
  • Release · February 24, 2026
  • Open weights
  • Reasoning

Intelligence

Intelligence Index

#121 of 266
  1. 17.518Muse Glimmer (High)
  2. 16.917Doubao Seed Code
  3. 16.717Gemma 4 26B A4B (Reasoning)
  4. 16.617Ring-2.6-1T
  5. 15.616K2 Horizon 3.7B
  6. 15.616Qwen3.5 122B A10B (Reasoning)
  7. 15.215Qwen3.6 35B A3B (Non-reasoning)
  8. 14.715Gemma 4 31B (Reasoning)
  9. 14.314ERNIE 5.0 Thinking Preview
  10. 14.214Nova 2.0 Pro Preview (Medium)
Data from Artificial Analysis

Evaluations

  • AA-Omniscience Accuracy24.4%#95
  • Humanity's Last Exam25.2%#91
  • Terminal-Bench 4.00%#96
  • AA-LCR76.3%#80
  • SciCode39.7%#107
  • CritPt0.6%#112
  • MMMU-Pro75%#48
  • GPQA Diamond85.7%#44
  • IFBench75.7%#9
  • τ²-Bench Telecom93.6%#6
  • τ²-Bench Banking15.3%#57
  • Terminal-Bench Hard31.1%#18
Qwen3.5 122B A10B (Reasoning)Median
Data from Artificial Analysis

Speed and price

Speed

tokens per second · #57 of 162
  1. 134134Claude Sonnet 5.5 (Max)
  2. 133133Qwen3 Next 80B A3B Instruct
  3. 132132Gemini 3.1 Pro Preview
  4. 131131Qwen3.6 35B A3B (Reasoning)
  5. 130130GPT-5.6 Terra (Max)
  6. 128128Qwen3.5 122B A10B (Reasoning)
  7. 127127GPT-6 Luna (Xhigh)
  8. 127127Nova 2.0 Pro Preview (Medium)
  9. 124124Ring-2.6-1T
  10. 122122NVIDIA Nemotron Nano 9B V2 (Reasoning)
Data from Artificial Analysis

Latency

seconds to first token · #89 of 162
  1. 2.22.2Qwen3.5 397B A17B (Reasoning)
  2. 2.22.2K2 Horizon 375B A23B
  3. 2.22.2GPT-5.6 Terra (High)
  4. 2.22.2Gemma 4 12B (Reasoning)
  5. 2.32.3Gemma 4 12B (Non-reasoning)
  6. 2.32.3Qwen3.5 122B A10B (Reasoning)
  7. 2.32.3Hermes 4 - Llama-3.1 405B (Non-reasoning)
  8. 2.32.3Qwen3.7 Plus
  9. 2.32.3Qwen3.5 122B A10B (Non-reasoning)
  10. 2.32.3Hermes 4 - Llama-3.1 405B (Reasoning)
Data from Artificial Analysis

Price

$ per 1M tokens (3:1) · #98 of 169
  1. $0.850.85Nova 2.0 Lite (Medium)
  2. $0.850.85Nova 2.0 Lite (Low)
  3. $0.850.85Nova 2.0 Lite (Non-reasoning)
  4. $0.980.98Apodex 1.1
  5. $1.11.1Qwen3.5 122B A10B (Non-reasoning)
  6. $1.11.1Qwen3.5 122B A10B (Reasoning)
  7. $1.131.13Qwen3.8 27B (Xhigh)
  8. $1.131.13Qwen3.8 27B (Medium)
  9. $1.131.13Qwen3.8 27B (Low)
  10. $1.131.13Nemotron 3 Ultra 550B A55B (Reasoning)
Data from Artificial Analysis

Nearby models

  • Muse Glimmer (High)Meta17.5
  • Doubao Seed CodeByteDance Seed16.9
  • Gemma 4 26B A4B (Reasoning)Google16.7
  • Ring-2.6-1TInclusionAI16.6
  • K2 Horizon 3.7BInstitute of Foundation Models15.6
  • Qwen3.6 35B A3B (Non-reasoning)Alibaba15.2
  • Gemma 4 31B (Reasoning)Google14.7
  • ERNIE 5.0 Thinking PreviewBaidu14.3
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
  • Qwen3.8 27B (Low)Alibaba26.2
  • Qwen3.7 PlusAlibaba25.2
  • Qwen3.5 397B A17B (Non-reasoning)Alibaba21.4
Data from Artificial Analysis
HorizonVascend IDEOlympusTalosCoursesCommunityBenchmark
DiscordGitHubXLet’s talkLegalPrivacyCookiesData useSecurity
© 2026 Vascend Technologies · VAT IT04911550616
ascend