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

Qwen3.5 9B (Reasoning)

  • Alibaba
  • Release · March 2, 2026
  • Open weights
  • Reasoning

Intelligence

Intelligence Index

#154 of 266
  1. 11.612gpt-oss-120b (High)
  2. 11.512K2 Think V2
  3. 11.512LongCat Flash Lite
  4. 11.411HyperCLOVA X SEED Think (32B)
  5. 11.311Mistral Small 4 (Reasoning)
  6. 11.211Qwen3.5 9B (Reasoning)
  7. 11.211Qwen3 Next 80B A3B (Reasoning)
  8. 11.111Granite 4.2 8B
  9. 11.111Ling 3.0 Tiny
  10. 11.111Nova 2.0 Omni (Low)
Data from Artificial Analysis

Evaluations

  • AA-Omniscience Accuracy16.4%#159
  • Humanity's Last Exam14.9%#117
  • Terminal-Bench 4.00.5%#86
  • AA-LCR70%#104
  • SciCode29.5%#126
  • CritPt0.3%#117
  • MMMU-Pro69.3%#65
  • GPQA Diamond80.6%#70
  • IFBench66.7%#23
  • τ²-Bench Telecom86.8%#21
  • τ²-Bench Banking7%#75
  • Terminal-Bench Hard24.2%#29
Qwen3.5 9B (Reasoning)Median
Data from Artificial Analysis

Speed and price

Speed

tokens per second · #121 of 162
  1. 6666GPT-6 Astra (Max)
  2. 6666North Mini Code
  3. 6464Kimi K2.7 Code
  4. 6363Claude Fable 5.1 (Xhigh)
  5. 6262GPT-6 Astra (Xhigh)
  6. 6161Qwen3.5 9B (Reasoning)
  7. 6060Qwen3.5 397B A17B (Non-reasoning)
  8. 5959Qwen3.5 397B A17B (Reasoning)
  9. 5959GPT-6.1 Sol (Max)
  10. 5858Claude Fable 5.1 (High)
Data from Artificial Analysis

Latency

seconds to first token · #77 of 162
  1. 1.81.8Ling 3.1 Flash
  2. 1.81.8Gemma 4 31B (Non-reasoning)
  3. 1.81.8Qwen3 Omni 30B A3B Instruct
  4. 1.91.9Solar Mini 4
  5. 1.91.9Qwen3 Omni 30B A3B (Reasoning)
  6. 1.91.9Qwen3.5 9B (Reasoning)
  7. 22Qwen3.5 Omni Plus
  8. 22Qwen3.6 35B A3B (Non-reasoning)
  9. 2.12.1GPT-6.1 Sol (Low)
  10. 2.12.1Qwen3.6 35B A3B (Reasoning)
Data from Artificial Analysis

Price

$ per 1M tokens (3:1) · #30 of 169
  1. $0.140.14Phi-4 Multimodal Instruct
  2. $0.150.15Agnes 2.5 Pro Beta
  3. $0.150.15Gemma 4 12B (Reasoning)
  4. $0.150.15Gemma 4 12B (Non-reasoning)
  5. $0.150.15Ministral 3 8B
  6. $0.150.15Qwen3.5 9B (Reasoning)
  7. $0.160.16Gemma 4 26B A4B (Reasoning)
  8. $0.170.17Quasar 438B (Max, Based on GLM-5.2)
  9. $0.180.18MiMo-V2.6-Flash
  10. $0.180.18Solar Mini 4
Data from Artificial Analysis

Nearby models

  • gpt-oss-120b (High)OpenAI11.6
  • K2 Think V2Institute of Foundation Models11.5
  • LongCat Flash LiteLongCat11.5
  • HyperCLOVA X SEED Think (32B)Naver11.4
  • Mistral Small 4 (Reasoning)Mistral11.3
  • Qwen3 Next 80B A3B (Reasoning)Alibaba11.2
  • Granite 4.2 8BIBM11.1
  • Ling 3.0 TinyInclusionAI11.1
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