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

LFM2.5-VL-1.6B

  • Liquid AI
  • Release · January 5, 2026
  • Open weights
  • Non-reasoning

Intelligence

Intelligence Index

#265 of 266
  1. 5.15.1Granite 4.0 Micro
  2. 55Molmo2-8B
  3. 4.84.8Granite 4.0 H 350M
  4. 4.84.8Granite 4.0 350M
  5. 4.84.8NVIDIA Nemotron 3 Nano 4B
  6. 4.84.8Ministral 3 3B
  7. 4.84.8Tiny Aya Global
  8. 4.84.8Apertus 8B Instruct
  9. 4.84.8LFM2.5-VL-1.6B
  10. 33K2 Horizon 0.9B
Data from Artificial Analysis

Evaluations

  • AA-Omniscience Accuracy5.8%#249
  • Humanity's Last Exam5.1%#206
  • AA-LCR0%#229
  • CritPt0%#143
  • MMMU-Pro26.5%#117
  • GPQA Diamond28.9%#202
  • IFBench33.1%#114
  • τ²-Bench Telecom8.5%#140
  • Terminal-Bench Hard0%#121
LFM2.5-VL-1.6BMedian
Data from Artificial Analysis

Nearby models

  • Granite 4.0 MicroIBM5.1
  • Molmo2-8BAllen Institute for AI5
  • Granite 4.0 H 350MIBM4.8
  • Granite 4.0 350MIBM4.8
  • NVIDIA Nemotron 3 Nano 4BNVIDIA4.8
  • Ministral 3 3BMistral4.8
  • Tiny Aya GlobalCohere4.8
  • Apertus 8B InstructSwiss AI Initiative4.8
Data from Artificial Analysis

Same lab

  • LFM2.5-2.6BLiquid AI8.4
  • LFM2.5-8B-A1BLiquid AI7.2
  • LFM2 24B A2BLiquid AI5.9
  • LFM2.5-1.2B-ThinkingLiquid AI5.2
  • LFM2.5-1.2B-InstructLiquid AI5.2
Data from Artificial Analysis
HorizonVascend IDEOlympusTalosCoursesCommunityBenchmark
DiscordGitHubXLet’s talkLegalPrivacyCookiesData useSecurity
© 2026 Vascend Technologies · VAT IT04911550616
ascend