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

Olmo 3 7B Instruct

  • Allen Institute for AI
  • Release · November 20, 2025
  • Open weights
  • Non-reasoning

Intelligence

Intelligence Index

#251 of 266
  1. 5.45.4Llama 3.2 Instruct 11B (Vision)
  2. 5.35.3Exaone 4.0 1.2B (Reasoning)
  3. 5.25.2LFM2.5-1.2B-Thinking
  4. 5.25.2LFM2.5-1.2B-Instruct
  5. 5.25.2Jamba 1.7 Mini
  6. 5.25.2Olmo 3 7B Instruct
  7. 5.25.2Granite 4.0 H 1B
  8. 5.25.2Exaone 4.0 1.2B (Non-reasoning)
  9. 5.15.1Gemma 3 270M
  10. 5.15.1DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning)
Data from Artificial Analysis

Evaluations

  • AA-Omniscience Accuracy7.4%#237
  • Humanity's Last Exam5.8%#193
  • AA-LCR0%#229
  • CritPt0%#143
  • GPQA Diamond40%#186
  • IFBench32.8%#115
  • τ²-Bench Telecom12.6%#132
  • Terminal-Bench Hard0%#121
Olmo 3 7B InstructMedian
Data from Artificial Analysis

Nearby models

  • Llama 3.2 Instruct 11B (Vision)Meta5.4
  • Exaone 4.0 1.2B (Reasoning)LG AI Research5.3
  • LFM2.5-1.2B-ThinkingLiquid AI5.2
  • LFM2.5-1.2B-InstructLiquid AI5.2
  • Jamba 1.7 MiniAI21 Labs5.2
  • Granite 4.0 H 1BIBM5.2
  • Exaone 4.0 1.2B (Non-reasoning)LG AI Research5.2
  • Gemma 3 270MGoogle5.1
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
  • Molmo2-8BAllen Institute for AI5
Data from Artificial Analysis
HorizonVascend IDEOlympusTalosCoursesCommunityBenchmark
DiscordGitHubXLet’s talkLegalPrivacyCookiesData useSecurity
© 2026 Vascend Technologies · VAT IT04911550616
ascend