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

Qwen3.5 4B (Reasoning)

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

Intelligence

Intelligence Index

#134 of 266
  1. 13.614Nova 2.0 Omni (Medium)
  2. 13.413Nova 2.0 Lite (High)
  3. 13.413Apriel-v1.6-15B-Thinker
  4. 13.313Qwen3.5 9B (Non-reasoning)
  5. 13.213EXAONE 4.5 33B (Reasoning)
  6. 13.113Qwen3.5 4B (Reasoning)
  7. 13.113Gemma 4 26B A4B (Non-reasoning)
  8. 13.113Command A+
  9. 12.913Nemotron 3.5 Lightning
  10. 12.813Nova 2.0 Pro Preview (Low)
Data from Artificial Analysis

Evaluations

  • AA-Omniscience Accuracy15.1%#174
  • Humanity's Last Exam9.9%#156
  • AA-LCR63%#125
  • CritPt0%#143
  • MMMU-Pro65.4%#73
  • GPQA Diamond77.1%#79
  • IFBench52%#57
  • τ²-Bench Telecom92.1%#11
  • τ²-Bench Banking6.8%#77
  • Terminal-Bench Hard18.2%#37
Qwen3.5 4B (Reasoning)Median
Data from Artificial Analysis

Speed and price

Speed

tokens per second · #161 of 162
  1. 4343Hermes 4 - Llama-3.1 405B (Non-reasoning)
  2. 4343Hermes 4 - Llama-3.1 405B (Reasoning)
  3. 4141Qwen3.8 2.4T A95B
  4. 4040Qwen3.8 Max (0902)
  5. 3939Phi-4
  6. 3535Gemma 4 31B (Reasoning)
  7. 3333Command A
  8. 2626Llama 3.2 Instruct 11B (Vision)
  9. 1919Qwen3.5 4B (Reasoning)
  10. 1414Qwen3.5 4B (Non-reasoning)
Data from Artificial Analysis

Latency

seconds to first token · #32 of 162
  1. 0.90.9GPT-5.5 Instant (June 2026)
  2. 0.90.9Qwen3.5 9B (Non-reasoning)
  3. 0.90.9Qwen3.5 4B (Non-reasoning)
  4. 0.90.9Gemma 4 E4B (Reasoning)
  5. 0.90.9Gemma 4 26B A4B (Reasoning)
  6. 0.90.9Qwen3.5 4B (Reasoning)
  7. 0.90.9Qwen3 Coder Next
  8. 0.90.9Mistral Small 4 (Non-reasoning)
  9. 11Gemma 4 26B A4B (Non-reasoning)
  10. 11gpt-oss-20b (Low)
Data from Artificial Analysis

Price

$ per 1M tokens (3:1) · #10 of 169
  1. $00North Mini Code
  2. $00Tiny Aya Global
  3. $0.040.04Gemma 4 E4B (Reasoning)
  4. $0.040.04Gemma 4 E4B (Non-reasoning)
  5. $0.050.05Granite 4.2 3B
  6. $0.060.06Qwen3.5 4B (Reasoning)
  7. $0.060.06Qwen3.5 4B (Non-reasoning)
  8. $0.060.06Nova Micro
  9. $0.070.07NVIDIA Nemotron Nano 9B V2 (Reasoning)
  10. $0.070.07Sarvam 105B (High)
Data from Artificial Analysis

Nearby models

  • Nova 2.0 Omni (Medium)Amazon13.6
  • Nova 2.0 Lite (High)Amazon13.4
  • Apriel-v1.6-15B-ThinkerServiceNow13.4
  • Qwen3.5 9B (Non-reasoning)Alibaba13.3
  • EXAONE 4.5 33B (Reasoning)LG AI Research13.2
  • Gemma 4 26B A4B (Non-reasoning)Google13.1
  • Command A+Cohere13.1
  • Nemotron 3.5 LightningNVIDIA12.9
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