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

Qwen3.8 Max (0902)

  • Alibaba
  • Release · September 2, 2026
  • Proprietary
  • Reasoning

Intelligence

Intelligence Index

#29 of 266
  1. 46.847Claude Fable 5.1 (Low)
  2. 46.446Grok 4.7 (Xhigh)
  3. 46.346MiMo-V2.6-Pro
  4. 46.346Grok 4.7 (High)
  5. 45.846GPT-6 Astra (Low)
  6. 45.445Qwen3.8 Max (0902)
  7. 45.145DeepSeek V4.1 Flash 1017 (Max)
  8. 44.845GLM-5.3 (Max)
  9. 43.944Ling 3.1 Flash 1019
  10. 43.744Step 5 Preview
Data from Artificial Analysis

Evaluations

  • AA-Briefcase1,611#8
  • AA-Omniscience Accuracy31.7%#74
  • AA-Omniscience Non-Hallucination71.2%#7
  • AutomationBench-AA56.2%#18
  • GDPval-AA1,666#10
  • Humanity's Last Exam43.1%#38
  • GDP.pdf22.8%#9
  • Terminal-Bench 4.038.9%#27
  • AA-LCR80.3%#41
  • SciCode52.1%#52
  • CritPt17.7%#45
  • Terminal-Bench-Science11.9%#12
  • FrontierCode43.2%#12
  • AA-AnalystAgent45%#11
  • EnterpriseOps-Gym-AA47.6%#1
  • AA-3D945#13
  • ITBench-AA40.3%#8
  • MLCR-AA20%#10
  • MMMU-Pro82.8%#20
  • PersonalityBench: Expressiveness16.2#25
  • PersonalityBench: Organization64.5#15
  • PersonalityBench: Transparency46.7#18
  • PersonalityBench: Slop74.6#5
  • PersonalityBench: Informativeness31.5#19
  • PersonalityBench: Warmth34#21
  • PersonalityBench: Conviction28.9#22
  • PersonalityBench: Imagination49.2#17
  • GPQA Diamond92.8%#13
  • τ²-Bench Banking47.8%#4
  • APEX-Agents42.4%#1
Qwen3.8 Max (0902)Median
Data from Artificial Analysis

Cost per task

Cost per task

$ per Intelligence Index task · #21 of 24
  1. $1.991.99Gemini 4 Argon (High)
  2. $2.012.01GLM-5.3 (Max)
  3. $2.112.11Kimi K3.1 Pro
  4. $3.263.26GPT-6 Astra (Max)
  5. $3.743.74Grok 4.7 (Xhigh)
  6. $4.544.54Muse Wonder (Max)
  7. $5.415.41Qwen3.8 Max (0902)
  8. $5.465.46Claude Sonnet 5.5 (Max)
  9. $5.985.98Claude Opus 5.5 (Max)
  10. $7.637.63Claude Fable 5.1 (Max)
Data from Artificial Analysis

Time per task

seconds per task · #26 of 26
  1. 723723Gemini 4 Argon (High)
  2. 736736Claude Fable 5.1 (Max)
  3. 791791Claude Opus 5.5 (Max)
  4. 824824GLM-5.3-Flash
  5. 846846Kimi K3.1 Pro
  6. 901901Grok 4.7 (Xhigh)
  7. 936936Claude Sonnet 5.5 (Max)
  8. 1,0131,013MiMo-V2.6-Pro
  9. 1,2001,200Qwen3.8 27B (Xhigh)
  10. 2,0572,057Qwen3.8 Max (0902)
Data from Artificial Analysis

Tokens per task

output tokens per task · #24 of 27
  1. 71K71KGemini 3.8 Flash (High)
  2. 71.1K71KGLM-5.3 (Max)
  3. 78.1K78KClaude Fable 5.1 (Max)
  4. 78.6K79KMiniMax-M3.1-Flash
  5. 80.6K81KGrok 4.7 (Xhigh)
  6. 89.5K90KDeepSeek V4.1 Flash 1017 (Max)
  7. 107.7K108KQwen3.8 Max (0902)
  8. 119.2K119KClaude Opus 5.5 (Max)
  9. 162.2K162KClaude Haiku 5.5 (Max)
  10. 197.4K197KClaude Sonnet 5.5 (Max)
Data from Artificial Analysis

Speed and price

Speed

tokens per second · #156 of 162
  1. 4545Qwen3.8 27B (Xhigh)
  2. 4545Gemma 4 E4B (Non-reasoning)
  3. 4343Hermes 4 - Llama-3.1 405B (Non-reasoning)
  4. 4343Hermes 4 - Llama-3.1 405B (Reasoning)
  5. 4141Qwen3.8 2.4T A95B
  6. 4040Qwen3.8 Max (0902)
  7. 3939Phi-4
  8. 3535Gemma 4 31B (Reasoning)
  9. 3333Command A
  10. 2626Llama 3.2 Instruct 11B (Vision)
Data from Artificial Analysis

Latency

seconds to first token · #104 of 162
  1. 2.62.6LongCat 2.0
  2. 2.62.6Ling 3.0 Tiny
  3. 2.82.8Hy3
  4. 2.82.8GPT-6 Luna (Medium)
  5. 2.82.8Kimi K2.7 Code
  6. 2.82.8Qwen3.8 Max (0902)
  7. 2.82.8GLM-5.3-Flash
  8. 2.92.9Qwen3.8 2.4T A95B
  9. 33GLM-5.3 (Low)
  10. 3.13.1Kimi K3.1 Pro
Data from Artificial Analysis

Price

$ per 1M tokens (3:1) · #124 of 169
  1. $2.072.07Mistral Large 4 Preview
  2. $2.152.15GLM-5.3 (Max)
  3. $2.152.15GLM-5.3 (Low)
  4. $33Grok 4.7 (Xhigh)
  5. $33Grok 4.7 (High)
  6. $33Qwen3.8 Max (0902)
  7. $33Grok 4.7 (Low)
  8. $33Qwen3.8 2.4T A95B
  9. $33Mistral Medium 3.5
  10. $3.443.44Nova 2.0 Pro Preview (Medium)
Data from Artificial Analysis

Nearby models

  • Claude Fable 5.1 (Low)Anthropic46.8
  • Grok 4.7 (Xhigh)SpaceXAI46.4
  • MiMo-V2.6-ProXiaomi46.3
  • Grok 4.7 (High)SpaceXAI46.3
  • GPT-6 Astra (Low)OpenAI45.8
  • DeepSeek V4.1 Flash 1017 (Max)DeepSeek45.1
  • GLM-5.3 (Max)Z AI44.8
  • Ling 3.1 Flash 1019InclusionAI43.9
Data from Artificial Analysis

Same lab

  • 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
  • Qwen3.5 Omni PlusAlibaba20.4
Data from Artificial Analysis
HorizonVascend IDEOlympusTalosCoursesCommunityBenchmark
DiscordGitHubXLet’s talkLegalPrivacyCookiesData useSecurity
© 2026 Vascend Technologies · VAT IT04911550616
ascend