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

Qwen3.6 35B A3B (Reasoning)

  • Alibaba
  • Release · April 16, 2026
  • Open weights
  • Reasoning

Intelligence

Intelligence Index

#114 of 266
  1. 19.720K-EXAONE 2.0 0803
  2. 19.119LongCat 2.0
  3. 18.719JT-35B-Flash
  4. 18.519GPT-6 Luna (Non-reasoning)
  5. 18.418Qwen3.5 397B A17B (Reasoning)
  6. 18.218Qwen3.6 35B A3B (Reasoning)
  7. 17.718Qwen3.5 122B A10B (Non-reasoning)
  8. 17.518Muse Glimmer (High)
  9. 16.917Doubao Seed Code
  10. 16.717Gemma 4 26B A4B (Reasoning)
Data from Artificial Analysis

Evaluations

  • AA-Omniscience Accuracy18.8%#126
  • Humanity's Last Exam22.2%#96
  • Terminal-Bench 4.00%#96
  • AA-LCR71.7%#96
  • SciCode36.6%#117
  • CritPt0.3%#117
  • MMMU-Pro75%#48
  • GPQA Diamond84.1%#55
  • IFBench64.4%#31
  • τ²-Bench Telecom95.3%#4
  • τ²-Bench Banking9.3%#70
  • Terminal-Bench Hard34.9%#16
Qwen3.6 35B A3B (Reasoning)Median
Data from Artificial Analysis

Speed and price

Speed

tokens per second · #55 of 162
  1. 137137Gemini 3.8 Flash (High)
  2. 136136Apertus 8B Instruct
  3. 134134Claude Sonnet 5.5 (Max)
  4. 133133Qwen3 Next 80B A3B Instruct
  5. 132132Gemini 3.1 Pro Preview
  6. 131131Qwen3.6 35B A3B (Reasoning)
  7. 130130GPT-5.6 Terra (Max)
  8. 128128Qwen3.5 122B A10B (Reasoning)
  9. 127127GPT-6 Luna (Xhigh)
  10. 127127Nova 2.0 Pro Preview (Medium)
Data from Artificial Analysis

Latency

seconds to first token · #81 of 162
  1. 1.91.9Qwen3 Omni 30B A3B (Reasoning)
  2. 1.91.9Qwen3.5 9B (Reasoning)
  3. 22Qwen3.5 Omni Plus
  4. 22Qwen3.6 35B A3B (Non-reasoning)
  5. 2.12.1GPT-6.1 Sol (Low)
  6. 2.12.1Qwen3.6 35B A3B (Reasoning)
  7. 2.12.1Qwen3.8-Flash-Next
  8. 2.22.2Qwen3.5 397B A17B (Non-reasoning)
  9. 2.22.2Qwen3.5 397B A17B (Reasoning)
  10. 2.22.2K2 Horizon 375B A23B
Data from Artificial Analysis

Price

$ per 1M tokens (3:1) · #88 of 169
  1. $0.640.64Nemotron 3 Nano Omni 30B A3B Reasoning
  2. $0.660.66DeepSeek V4 Flash Vision (Max)
  3. $0.670.67Llama 3.3 Instruct 70B
  4. $0.70.7Qwen3.7 Plus
  5. $0.750.75Magistral Small 1.2
  6. $0.840.84Qwen3.6 35B A3B (Reasoning)
  7. $0.840.84Qwen3.6 35B A3B (Non-reasoning)
  8. $0.850.85Gemini 3.5 Flash-Lite
  9. $0.850.85Ring-2.6-1T
  10. $0.850.85Nova 2.0 Lite (High)
Data from Artificial Analysis

Nearby models

  • K-EXAONE 2.0 0803LG AI Research19.7
  • LongCat 2.0LongCat19.1
  • JT-35B-FlashChina Mobile18.7
  • GPT-6 Luna (Non-reasoning)OpenAI18.5
  • Qwen3.5 397B A17B (Reasoning)Alibaba18.4
  • Qwen3.5 122B A10B (Non-reasoning)Alibaba17.7
  • Muse Glimmer (High)Meta17.5
  • Doubao Seed CodeByteDance Seed16.9
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