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

EXAONE 4.0 32B (Non-reasoning)

  • LG AI Research
  • Release · July 15, 2025
  • Open weights
  • Non-reasoning

Intelligence

Intelligence Index

#224 of 266
  1. 6.56.5Gemma 4 E2B (Non-reasoning)
  2. 6.56.5Llama 4 Scout
  3. 6.56.5Olmo 3.1 32B Instruct
  4. 6.46.4R1 1776
  5. 6.46.4Llama 3.2 Instruct 90B (Vision)
  6. 6.36.3EXAONE 4.0 32B (Non-reasoning)
  7. 6.36.3Celeris-1
  8. 6.36.3Phi-4 Mini Instruct
  9. 6.26.2Qwen3.5 2B (Non-reasoning)
  10. 6.16.1DeepHermes 3 - Mistral 24B Preview (Non-reasoning)
Data from Artificial Analysis

Evaluations

  • AA-Omniscience Accuracy10.6%#216
  • Humanity's Last Exam5%#210
  • CritPt0%#143
  • GPQA Diamond62.8%#139
  • IFBench33.5%#112
  • τ²-Bench Telecom4.1%#142
  • Terminal-Bench Hard1.5%#108
EXAONE 4.0 32B (Non-reasoning)Median
Data from Artificial Analysis

Nearby models

  • Gemma 4 E2B (Non-reasoning)Google6.5
  • Llama 4 ScoutMeta6.5
  • Olmo 3.1 32B InstructAllen Institute for AI6.5
  • R1 1776Perplexity6.4
  • Llama 3.2 Instruct 90B (Vision)Meta6.4
  • Celeris-1Celeris6.3
  • Phi-4 Mini InstructMicrosoft6.3
  • Qwen3.5 2B (Non-reasoning)Alibaba6.2
Data from Artificial Analysis

Same lab

  • K-EXAONE 2.0 0803LG AI Research19.7
  • EXAONE 4.5 33B (Reasoning)LG AI Research13.2
  • EXAONE 4.0 32B (Reasoning)LG AI Research8.2
  • Exaone 4.0 1.2B (Reasoning)LG AI Research5.3
  • Exaone 4.0 1.2B (Non-reasoning)LG AI Research5.2
Data from Artificial Analysis
HorizonVascend IDEOlympusTalosCoursesCommunityBenchmark
DiscordGitHubXLet’s talkLegalPrivacyCookiesData useSecurity
© 2026 Vascend Technologies · VAT IT04911550616
ascend