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

Qwen3 Next 80B A3B Instruct

  • Alibaba
  • Release · September 11, 2025
  • Open weights
  • Non-reasoning

Intelligence

Intelligence Index

#171 of 266
  1. 10.210gpt-oss-120b (Low)
  2. 1010Nova 2.0 Pro Preview (Non-reasoning)
  3. 1010gpt-oss-20b (Low)
  4. 9.910North Mini Code
  5. 9.910K2-V2 (High)
  6. 9.610Qwen3 Next 80B A3B Instruct
  7. 9.510DiffusionGemma 26B A4B
  8. 9.49.4Gemma 4 12B (Non-reasoning)
  9. 9.39.3Llama 4 Maverick
  10. 9.29.2Qwen3 Coder Next
Data from Artificial Analysis

Evaluations

  • AA-Omniscience Accuracy17.3%#146
  • Humanity's Last Exam7.7%#170
  • AA-LCR52.7%#141
  • CritPt0%#143
  • GPQA Diamond73.8%#101
  • IFBench39.7%#88
  • τ²-Bench Telecom21.6%#101
  • Terminal-Bench Hard7.6%#68
Qwen3 Next 80B A3B InstructMedian
Data from Artificial Analysis

Speed and price

Speed

tokens per second · #53 of 162
  1. 143143Qwen3.5 122B A10B (Non-reasoning)
  2. 140140GPT-6 Luna (Max)
  3. 137137Gemini 3.8 Flash (High)
  4. 136136Apertus 8B Instruct
  5. 134134Claude Sonnet 5.5 (Max)
  6. 133133Qwen3 Next 80B A3B Instruct
  7. 132132Gemini 3.1 Pro Preview
  8. 131131Qwen3.6 35B A3B (Reasoning)
  9. 130130GPT-5.6 Terra (Max)
  10. 128128Qwen3.5 122B A10B (Reasoning)
Data from Artificial Analysis

Latency

seconds to first token · #12 of 162
  1. 0.70.7Beam 1.0
  2. 0.70.7Nemotron 3.5 Super VL
  3. 0.70.7Granite 4.2 3B
  4. 0.80.8GPT-5.6 Terra (Non-reasoning)
  5. 0.80.8gpt-oss-120b (Low)
  6. 0.80.8Qwen3 Next 80B A3B Instruct
  7. 0.80.8gpt-oss-20b (High)
  8. 0.80.8Llama 4 Scout
  9. 0.80.8Muse Spark Open (Xhigh)
  10. 0.80.8gpt-oss-120b (High)
Data from Artificial Analysis

Price

$ per 1M tokens (3:1) · #66 of 169
  1. $0.30.3Llama 4 Scout
  2. $0.30.3NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)
  3. $0.310.31Nemotron 3.5 Super VL
  4. $0.330.33Celeris-1
  5. $0.350.35Llama 3.2 Instruct 11B (Vision)
  6. $0.350.35Qwen3 Next 80B A3B Instruct
  7. $0.350.35Reka Flash 3
  8. $0.380.38Mercury 2.5
  9. $0.390.39Trinity Large Thinking
  10. $0.420.42Llama 4 Maverick
Data from Artificial Analysis

Nearby models

  • gpt-oss-120b (Low)OpenAI10.2
  • Nova 2.0 Pro Preview (Non-reasoning)Amazon10
  • gpt-oss-20b (Low)OpenAI10
  • North Mini CodeCohere9.9
  • K2-V2 (High)Institute of Foundation Models9.9
  • DiffusionGemma 26B A4BGoogle9.5
  • Gemma 4 12B (Non-reasoning)Google9.4
  • Llama 4 MaverickMeta9.3
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