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

Qwen3.6 35B A3B (Non-reasoning)

  • Alibaba
  • Open weights
  • Non-reasoning

Intelligence

Intelligence Index

#122 of 266
  1. 16.917Doubao Seed Code
  2. 16.717Gemma 4 26B A4B (Reasoning)
  3. 16.617Ring-2.6-1T
  4. 15.616K2 Horizon 3.7B
  5. 15.616Qwen3.5 122B A10B (Reasoning)
  6. 15.215Qwen3.6 35B A3B (Non-reasoning)
  7. 14.715Gemma 4 31B (Reasoning)
  8. 14.314ERNIE 5.0 Thinking Preview
  9. 14.214Nova 2.0 Pro Preview (Medium)
  10. 14.214Mistral Medium 3.5
Data from Artificial Analysis

Evaluations

  • AA-Omniscience Accuracy16.7%#153
  • Humanity's Last Exam13.9%#122
  • AA-LCR64.3%#119
  • CritPt0%#143
  • MMMU-Pro71%#58
  • GPQA Diamond81.7%#67
  • IFBench36.2%#102
  • τ²-Bench Telecom85.1%#25
  • τ²-Bench Banking5.4%#87
  • Terminal-Bench Hard25.8%#25
Qwen3.6 35B A3B (Non-reasoning)Median
Data from Artificial Analysis

Speed and price

Speed

tokens per second · #47 of 162
  1. 159159Quasar 438B (Max, Based on GLM-5.2)
  2. 158158Nemotron 3 Ultra 550B A55B (Reasoning)
  3. 152152GPT-5.5 Instant (June 2026)
  4. 152152o3
  5. 151151Muse Spark Open (Xhigh)
  6. 147147Qwen3.6 35B A3B (Non-reasoning)
  7. 143143Qwen3.5 122B A10B (Non-reasoning)
  8. 140140GPT-6 Luna (Max)
  9. 137137Gemini 3.8 Flash (High)
  10. 136136Apertus 8B Instruct
Data from Artificial Analysis

Latency

seconds to first token · #79 of 162
  1. 1.81.8Qwen3 Omni 30B A3B Instruct
  2. 1.91.9Solar Mini 4
  3. 1.91.9Qwen3 Omni 30B A3B (Reasoning)
  4. 1.91.9Qwen3.5 9B (Reasoning)
  5. 22Qwen3.5 Omni Plus
  6. 22Qwen3.6 35B A3B (Non-reasoning)
  7. 2.12.1GPT-6.1 Sol (Low)
  8. 2.12.1Qwen3.6 35B A3B (Reasoning)
  9. 2.12.1Qwen3.8-Flash-Next
  10. 2.22.2Qwen3.5 397B A17B (Non-reasoning)
Data from Artificial Analysis

Price

$ per 1M tokens (3:1) · #89 of 169
  1. $0.660.66DeepSeek V4 Flash Vision (Max)
  2. $0.670.67Llama 3.3 Instruct 70B
  3. $0.70.7Qwen3.7 Plus
  4. $0.750.75Magistral Small 1.2
  5. $0.840.84Qwen3.6 35B A3B (Reasoning)
  6. $0.840.84Qwen3.6 35B A3B (Non-reasoning)
  7. $0.850.85Gemini 3.5 Flash-Lite
  8. $0.850.85Ring-2.6-1T
  9. $0.850.85Nova 2.0 Lite (High)
  10. $0.850.85Nova 2.0 Lite (Medium)
Data from Artificial Analysis

Nearby models

  • 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
  • Qwen3.5 122B A10B (Reasoning)Alibaba15.6
  • Gemma 4 31B (Reasoning)Google14.7
  • ERNIE 5.0 Thinking PreviewBaidu14.3
  • Nova 2.0 Pro Preview (Medium)Amazon14.2
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