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

Olmo 3 7B Think

  • Allen Institute for AI
  • Release · November 20, 2025
  • Open weights
  • Reasoning

Intelligence

Intelligence Index

#241 of 266
  1. 5.95.9LFM2 24B A2B
  2. 5.85.8NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)
  3. 5.85.8Phi-4 Multimodal Instruct
  4. 5.75.7MiniCPM-V 4.6 1.3B
  5. 5.75.7Jamba Reasoning 3B
  6. 5.65.6Olmo 3 7B Think
  7. 5.65.6Molmo 7B-D
  8. 5.65.6Reka Flash 3
  9. 5.55.5Ministral 3 8B
  10. 5.45.4Qwen3.5 0.8B (Non-reasoning)
Data from Artificial Analysis

Evaluations

  • AA-Omniscience Accuracy11.1%#213
  • Humanity's Last Exam6%#189
  • AA-LCR0%#229
  • CritPt0%#143
  • GPQA Diamond51.6%#165
  • IFBench41.5%#82
  • τ²-Bench Telecom0%#143
  • Terminal-Bench Hard0.8%#115
Olmo 3 7B ThinkMedian
Data from Artificial Analysis

Nearby models

  • LFM2 24B A2BLiquid AI5.9
  • NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)NVIDIA5.8
  • Phi-4 Multimodal InstructMicrosoft5.8
  • MiniCPM-V 4.6 1.3BOpenBMB5.7
  • Jamba Reasoning 3BAI21 Labs5.7
  • Molmo 7B-DAllen Institute for AI5.6
  • Reka Flash 3Reka AI5.6
  • Ministral 3 8BMistral5.5
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 InstructAllen Institute for AI5.2
  • Molmo2-8BAllen Institute for AI5
Data from Artificial Analysis
HorizonVascend IDEOlympusTalosCoursesCommunityBenchmark
DiscordGitHubXLet’s talkLegalPrivacyCookiesData useSecurity
© 2026 Vascend Technologies · VAT IT04911550616
ascend