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

Ling 3.0 Tiny

  • InclusionAI
  • Release · August 6, 2026
  • Open weights
  • Reasoning

Intelligence

Intelligence Index

#157 of 266
  1. 11.411HyperCLOVA X SEED Think (32B)
  2. 11.311Mistral Small 4 (Reasoning)
  3. 11.211Qwen3.5 9B (Reasoning)
  4. 11.211Qwen3 Next 80B A3B (Reasoning)
  5. 11.111Granite 4.2 8B
  6. 11.111Ling 3.0 Tiny
  7. 11.111Nova 2.0 Omni (Low)
  8. 1111Mi:dm K 2.5 Pro
  9. 10.811Trinity Large Thinking
  10. 10.811G9v3-3B
Data from Artificial Analysis

Evaluations

  • AA-Omniscience Accuracy8.5%#232
  • Humanity's Last Exam9.3%#162
  • Terminal-Bench 4.00%#96
  • AA-LCR60.3%#128
  • SciCode24.2%#131
  • CritPt0%#143
  • GPQA Diamond73.4%#104
  • τ²-Bench Banking20.8%#44
Ling 3.0 TinyMedian
Data from Artificial Analysis

Speed and price

Speed

tokens per second · #126 of 162
  1. 6161Qwen3.5 9B (Reasoning)
  2. 6060Qwen3.5 397B A17B (Non-reasoning)
  3. 5959Qwen3.5 397B A17B (Reasoning)
  4. 5959GPT-6.1 Sol (Max)
  5. 5858Claude Fable 5.1 (High)
  6. 5858Ling 3.0 Tiny
  7. 5858Kimi K3.1 Pro
  8. 5757Claude Fable 5.1 (Low)
  9. 5757MiMo-V2.6-Pro
  10. 5757GPT-6 Astra (High)
Data from Artificial Analysis

Latency

seconds to first token · #100 of 162
  1. 2.42.4Mistral Medium 3.5
  2. 2.42.4GLM-5.3 (Max)
  3. 2.52.5GPT-6 Luna (Low)
  4. 2.52.5Phi-4
  5. 2.62.6LongCat 2.0
  6. 2.62.6Ling 3.0 Tiny
  7. 2.82.8Hy3
  8. 2.82.8GPT-6 Luna (Medium)
  9. 2.82.8Kimi K2.7 Code
  10. 2.82.8Qwen3.8 Max (0902)
Data from Artificial Analysis

Price

$ per 1M tokens (3:1) · #4 of 169
  1. $00K2 Horizon 375B A23B
  2. $00Gemma 4 31B (Reasoning)
  3. $00Command A+
  4. $00Ling 3.0 Tiny
  5. $00North Mini Code
  6. $00Tiny Aya Global
  7. $0.040.04Gemma 4 E4B (Reasoning)
  8. $0.040.04Gemma 4 E4B (Non-reasoning)
  9. $0.050.05Granite 4.2 3B
  10. $0.060.06Qwen3.5 4B (Reasoning)
Data from Artificial Analysis

Nearby models

  • HyperCLOVA X SEED Think (32B)Naver11.4
  • Mistral Small 4 (Reasoning)Mistral11.3
  • Qwen3.5 9B (Reasoning)Alibaba11.2
  • Qwen3 Next 80B A3B (Reasoning)Alibaba11.2
  • Granite 4.2 8BIBM11.1
  • Nova 2.0 Omni (Low)Amazon11.1
  • Mi:dm K 2.5 ProKorea Telecom11
  • Trinity Large ThinkingArcee AI10.8
Data from Artificial Analysis

Same lab

  • Ling 3.1 Flash 1019InclusionAI43.9
  • Ling 3.1 FlashInclusionAI41.1
  • Ling-3.0-flash-VLInclusionAI24.6
  • Ling-3.0-flash-FinInclusionAI22.6
  • Ring-2.6-1TInclusionAI16.6
  • Ring-flash-2.0InclusionAI7.2
Data from Artificial Analysis
HorizonVascend IDEOlympusTalosCoursesCommunityBenchmark
DiscordGitHubXLet’s talkLegalPrivacyCookiesData useSecurity
© 2026 Vascend Technologies · VAT IT04911550616
ascend