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

Llama 4 Scout

  • Meta
  • Release · April 5, 2025
  • Open weights
  • Non-reasoning

Intelligence

Intelligence Index

#220 of 266
  1. 6.86.8NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)
  2. 6.86.8NVIDIA Nemotron Nano 9B V2 (Non-reasoning)
  3. 6.76.7Hermes 4 - Llama-3.1 70B (Non-reasoning)
  4. 6.66.6Sarvam 30B (High)
  5. 6.56.5Gemma 4 E2B (Non-reasoning)
  6. 6.56.5Llama 4 Scout
  7. 6.56.5Olmo 3.1 32B Instruct
  8. 6.46.4R1 1776
  9. 6.46.4Llama 3.2 Instruct 90B (Vision)
  10. 6.36.3EXAONE 4.0 32B (Non-reasoning)
Data from Artificial Analysis

Evaluations

  • AA-Omniscience Accuracy15.2%#170
  • Humanity's Last Exam3.8%#248
  • Terminal-Bench 4.00%#96
  • AA-LCR27.7%#179
  • SciCode21.3%#135
  • CritPt0%#143
  • MMMU-Pro53%#97
  • GPQA Diamond58.7%#147
  • IFBench39.5%#89
  • τ²-Bench Telecom15.5%#124
  • τ²-Bench Banking3.3%#98
  • Terminal-Bench Hard1.5%#108
Llama 4 ScoutMedian
Data from Artificial Analysis

Speed and price

Speed

tokens per second · #70 of 162
  1. 120120Nova 2.0 Pro Preview (Low)
  2. 120120GPT-6 Luna (High)
  3. 119119Ministral 3 8B
  4. 119119GPT-5.6 Terra (High)
  5. 118118GPT-5.6 Terra (Xhigh)
  6. 118118Llama 4 Scout
  7. 118118Gemma 4 12B (Non-reasoning)
  8. 116116GPT-6 Luna (Low)
  9. 116116GPT-5.6 Terra (Low)
  10. 115115Nova 2.0 Pro Preview (Non-reasoning)
Data from Artificial Analysis

Latency

seconds to first token · #14 of 162
  1. 0.70.7Granite 4.2 3B
  2. 0.80.8GPT-5.6 Terra (Non-reasoning)
  3. 0.80.8gpt-oss-120b (Low)
  4. 0.80.8Qwen3 Next 80B A3B Instruct
  5. 0.80.8gpt-oss-20b (High)
  6. 0.80.8Llama 4 Scout
  7. 0.80.8Muse Spark Open (Xhigh)
  8. 0.80.8gpt-oss-120b (High)
  9. 0.80.8Granite 4.2 8B
  10. 0.80.8Gemma 4 E4B (Non-reasoning)
Data from Artificial Analysis

Price

$ per 1M tokens (3:1) · #61 of 169
  1. $0.260.26gpt-oss-120b (High)
  2. $0.260.26Mistral Small 4 (Reasoning)
  3. $0.260.26Mistral Small 4 (Non-reasoning)
  4. $0.280.28Qwen3.5 Omni Flash
  5. $0.280.28Granite 4.2 30B
  6. $0.30.3Llama 4 Scout
  7. $0.30.3NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)
  8. $0.310.31Nemotron 3.5 Super VL
  9. $0.330.33Celeris-1
  10. $0.350.35Llama 3.2 Instruct 11B (Vision)
Data from Artificial Analysis

Nearby models

  • NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)NVIDIA6.8
  • NVIDIA Nemotron Nano 9B V2 (Non-reasoning)NVIDIA6.8
  • Hermes 4 - Llama-3.1 70B (Non-reasoning)Nous Research6.7
  • Sarvam 30B (High)Sarvam6.6
  • Gemma 4 E2B (Non-reasoning)Google6.5
  • Olmo 3.1 32B InstructAllen Institute for AI6.5
  • R1 1776Perplexity6.4
  • Llama 3.2 Instruct 90B (Vision)Meta6.4
Data from Artificial Analysis

Same lab

  • Muse Wonder Full (Max)Meta55.8
  • Muse Wonder (Max)Meta52.4
  • Muse Spark Open (Xhigh)Meta38.9
  • Muse Glimmer (High)Meta17.5
  • Llama 4 MaverickMeta9.3
  • Llama 3.3 Instruct 70BMeta7.7
  • Llama 3.1 Instruct 405BMeta7.3
  • Llama 3.2 Instruct 11B (Vision)Meta5.4
Data from Artificial Analysis
HorizonVascend IDEOlympusTalosCoursesCommunityBenchmark
DiscordGitHubXLet’s talkLegalPrivacyCookiesData useSecurity
© 2026 Vascend Technologies · VAT IT04911550616
ascend