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

LongCat 2.0

  • LongCat
  • Release · June 29, 2026
  • Open weights
  • Reasoning

Intelligence

Intelligence Index

#110 of 266
  1. 20.420Qwen3.5 Omni Plus
  2. 20.420DeepSeek V4 Pro 0813 (Non-reasoning)
  3. 20.220o3
  4. 20.220Qwen3.8 27B (Non-reasoning)
  5. 19.720K-EXAONE 2.0 0803
  6. 19.119LongCat 2.0
  7. 18.719JT-35B-Flash
  8. 18.519GPT-6 Luna (Non-reasoning)
  9. 18.418Qwen3.5 397B A17B (Reasoning)
  10. 18.218Qwen3.6 35B A3B (Reasoning)
Data from Artificial Analysis

Evaluations

  • AA-Omniscience Accuracy29.6%#81
  • Humanity's Last Exam33.7%#73
  • Terminal-Bench 4.00%#96
  • AA-LCR65%#117
  • SciCode36.3%#118
  • CritPt2.6%#91
  • GPQA Diamond78%#77
  • τ²-Bench Banking13.2%#64
LongCat 2.0Median
Data from Artificial Analysis

Speed and price

Speed

tokens per second · #113 of 162
  1. 8080Claude Opus 5.5 (High)
  2. 8080Qwen3.5 9B (Non-reasoning)
  3. 7878Grok 4.7 (Low)
  4. 7777Ministral 3 14B
  5. 7777Magistral Small 1.2
  6. 7676LongCat 2.0
  7. 7070GLM-5.3-Flash
  8. 7070Claude Fable 5.1 (Max)
  9. 6666GPT-6 Astra (Max)
  10. 6666North Mini Code
Data from Artificial Analysis

Latency

seconds to first token · #99 of 162
  1. 2.32.3GPT-6 Astra (Low)
  2. 2.42.4Mistral Medium 3.5
  3. 2.42.4GLM-5.3 (Max)
  4. 2.52.5GPT-6 Luna (Low)
  5. 2.52.5Phi-4
  6. 2.62.6LongCat 2.0
  7. 2.62.6Ling 3.0 Tiny
  8. 2.82.8Hy3
  9. 2.82.8GPT-6 Luna (Medium)
  10. 2.82.8Kimi K2.7 Code
Data from Artificial Analysis

Price

$ per 1M tokens (3:1) · #104 of 169
  1. $1.131.13Qwen3.8 27B (Xhigh)
  2. $1.131.13Qwen3.8 27B (Medium)
  3. $1.131.13Qwen3.8 27B (Low)
  4. $1.131.13Nemotron 3 Ultra 550B A55B (Reasoning)
  5. $1.131.13Qwen3.8 27B (Non-reasoning)
  6. $1.31.3LongCat 2.0
  7. $1.351.35Qwen3.5 397B A17B (Non-reasoning)
  8. $1.351.35Qwen3.5 397B A17B (Reasoning)
  9. $1.431.43Step 5 Preview
  10. $1.51.5Gemini 3.8 Flash (High)
Data from Artificial Analysis

Nearby models

  • Qwen3.5 Omni PlusAlibaba20.4
  • DeepSeek V4 Pro 0813 (Non-reasoning)DeepSeek20.4
  • o3OpenAI20.2
  • Qwen3.8 27B (Non-reasoning)Alibaba20.2
  • K-EXAONE 2.0 0803LG AI Research19.7
  • JT-35B-FlashChina Mobile18.7
  • GPT-6 Luna (Non-reasoning)OpenAI18.5
  • Qwen3.5 397B A17B (Reasoning)Alibaba18.4
Data from Artificial Analysis

Same lab

  • LongCat Flash LiteLongCat11.5
Data from Artificial Analysis
HorizonVascend IDEOlympusTalosCoursesCommunityBenchmark
DiscordGitHubXLet’s talkLegalPrivacyCookiesData useSecurity
© 2026 Vascend Technologies · VAT IT04911550616
ascend