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

LFM2.5-8B-A1B

  • Liquid AI
  • Release · May 28, 2026
  • Open weights
  • Reasoning

Intelligence

Intelligence Index

#210 of 266
  1. 7.47.4Hermes 4 - Llama-3.1 405B (Non-reasoning)
  2. 7.47.4NVIDIA Nemotron Nano 9B V2 (Reasoning)
  3. 7.37.3K2-V2 (Low)
  4. 7.37.3Llama 3.1 Instruct 405B
  5. 7.37.3Kimi Linear 48B A3B Instruct
  6. 7.27.2LFM2.5-8B-A1B
  7. 7.27.2Ring-flash-2.0
  8. 7.17.1Olmo 3.1 32B Think
  9. 77Command A
  10. 6.96.9Qwen3.5 2B (Reasoning)
Data from Artificial Analysis

Evaluations

  • AA-Omniscience Accuracy9.3%#225
  • Humanity's Last Exam6.9%#176
  • AA-LCR0%#229
  • CritPt0%#143
  • GPQA Diamond51.3%#168
  • IFBench55.7%#51
  • τ²-Bench Telecom16.1%#121
  • Terminal-Bench Hard4.6%#81
LFM2.5-8B-A1BMedian
Data from Artificial Analysis

Nearby models

  • Hermes 4 - Llama-3.1 405B (Non-reasoning)Nous Research7.4
  • NVIDIA Nemotron Nano 9B V2 (Reasoning)NVIDIA7.4
  • K2-V2 (Low)Institute of Foundation Models7.3
  • Llama 3.1 Instruct 405BMeta7.3
  • Kimi Linear 48B A3B InstructKimi7.3
  • Ring-flash-2.0InclusionAI7.2
  • Olmo 3.1 32B ThinkAllen Institute for AI7.1
  • Command ACohere7
Data from Artificial Analysis

Same lab

  • LFM2.5-2.6BLiquid AI8.4
  • LFM2 24B A2BLiquid AI5.9
  • LFM2.5-1.2B-ThinkingLiquid AI5.2
  • LFM2.5-1.2B-InstructLiquid AI5.2
  • LFM2.5-VL-1.6BLiquid AI4.8
Data from Artificial Analysis
HorizonVascend IDEOlympusTalosCoursesCommunityBenchmark
DiscordGitHubXLet’s talkLegalPrivacyCookiesData useSecurity
© 2026 Vascend Technologies · VAT IT04911550616
ascend