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

Molmo2-8B

  • Allen Institute for AI
  • Release · December 11, 2025
  • Open weights
  • Non-reasoning

Intelligence

Intelligence Index

#258 of 266
  1. 5.25.2Exaone 4.0 1.2B (Non-reasoning)
  2. 5.15.1Gemma 3 270M
  3. 5.15.1DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning)
  4. 5.15.1Apertus 70B Instruct
  5. 5.15.1Granite 4.0 Micro
  6. 55Molmo2-8B
  7. 4.84.8Granite 4.0 H 350M
  8. 4.84.8Granite 4.0 350M
  9. 4.84.8NVIDIA Nemotron 3 Nano 4B
  10. 4.84.8Ministral 3 3B
Data from Artificial Analysis

Evaluations

  • AA-Omniscience Accuracy11.5%#208
  • Humanity's Last Exam4.3%#236
  • AA-LCR0%#229
  • CritPt0%#143
  • MMMU-Pro37.5%#115
  • GPQA Diamond42.5%#181
  • IFBench26.9%#134
  • τ²-Bench Telecom0%#143
  • Terminal-Bench Hard0%#121
Molmo2-8BMedian
Data from Artificial Analysis

Nearby models

  • Exaone 4.0 1.2B (Non-reasoning)LG AI Research5.2
  • Gemma 3 270MGoogle5.1
  • DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning)Nous Research5.1
  • Apertus 70B InstructSwiss AI Initiative5.1
  • Granite 4.0 MicroIBM5.1
  • Granite 4.0 H 350MIBM4.8
  • Granite 4.0 350MIBM4.8
  • NVIDIA Nemotron 3 Nano 4BNVIDIA4.8
Data from Artificial Analysis

Same lab

  • Olmo 3.1 32B ThinkAllen Institute for AI7.1
  • Olmo 3.1 32B InstructAllen Institute for AI6.5
  • Olmo 3 7B ThinkAllen Institute for AI5.6
  • Molmo 7B-DAllen Institute for AI5.6
  • Olmo 3 7B InstructAllen Institute for AI5.2
Data from Artificial Analysis
HorizonVascend IDEOlympusTalosCoursesCommunityBenchmark
DiscordGitHubXLet’s talkLegalPrivacyCookiesData useSecurity
© 2026 Vascend Technologies · VAT IT04911550616
ascend