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

Jamba 1.7 Large

  • AI21 Labs
  • Release · July 7, 2025
  • Open weights
  • Non-reasoning

Intelligence

Intelligence Index

#229 of 266
  1. 6.36.3EXAONE 4.0 32B (Non-reasoning)
  2. 6.36.3Celeris-1
  3. 6.36.3Phi-4 Mini Instruct
  4. 6.26.2Qwen3.5 2B (Non-reasoning)
  5. 6.16.1DeepHermes 3 - Mistral 24B Preview (Non-reasoning)
  6. 6.16.1Jamba 1.7 Large
  7. 6.16.1Qwen3.5 0.8B (Reasoning)
  8. 66Ministral 3 14B
  9. 66Qwen3 Omni 30B A3B Instruct
  10. 66Granite 4.0 H Small
Data from Artificial Analysis

Evaluations

  • AA-Omniscience Accuracy20.6%#113
  • Humanity's Last Exam3.7%#255
  • AA-LCR19.3%#197
  • CritPt0%#143
  • GPQA Diamond39%#188
  • IFBench35.2%#105
  • τ²-Bench Telecom13.5%#129
  • Terminal-Bench Hard2.3%#100
Jamba 1.7 LargeMedian
Data from Artificial Analysis

Nearby models

  • EXAONE 4.0 32B (Non-reasoning)LG AI Research6.3
  • Celeris-1Celeris6.3
  • Phi-4 Mini InstructMicrosoft6.3
  • Qwen3.5 2B (Non-reasoning)Alibaba6.2
  • DeepHermes 3 - Mistral 24B Preview (Non-reasoning)Nous Research6.1
  • Qwen3.5 0.8B (Reasoning)Alibaba6.1
  • Ministral 3 14BMistral6
  • Qwen3 Omni 30B A3B InstructAlibaba6
Data from Artificial Analysis

Same lab

  • Jamba Reasoning 3BAI21 Labs5.7
  • Jamba 1.7 MiniAI21 Labs5.2
Data from Artificial Analysis
HorizonVascend IDEOlympusTalosCoursesCommunityBenchmark
DiscordGitHubXLet’s talkLegalPrivacyCookiesData useSecurity
© 2026 Vascend Technologies · VAT IT04911550616
ascend