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

Llama 4 Maverick

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

Intelligence

Intelligence Index

#174 of 266
  1. 9.910North Mini Code
  2. 9.910K2-V2 (High)
  3. 9.610Qwen3 Next 80B A3B Instruct
  4. 9.510DiffusionGemma 26B A4B
  5. 9.49.4Gemma 4 12B (Non-reasoning)
  6. 9.39.3Llama 4 Maverick
  7. 9.29.2Qwen3 Coder Next
  8. 9.29.2Motif-2-12.7B-Reasoning
  9. 9.29.2Nova Premier
  10. 9.19.1Granite 4.2 3B
Data from Artificial Analysis

Evaluations

  • AA-Omniscience Accuracy24.9%#90
  • Humanity's Last Exam4.9%#217
  • Terminal-Bench 4.00%#96
  • AA-LCR50%#146
  • SciCode31.7%#123
  • CritPt0%#143
  • MMMU-Pro62.1%#84
  • GPQA Diamond67.1%#127
  • IFBench43%#78
  • τ²-Bench Telecom17.8%#116
  • τ²-Bench Banking3.7%#96
  • Terminal-Bench Hard6.8%#71
Llama 4 MaverickMedian
Data from Artificial Analysis

Speed and price

Speed

tokens per second · #141 of 162
  1. 5353GPT-6.1 Sol (High)
  2. 5353GPT-6 Astra (Medium)
  3. 5353GPT-6.1 Sol (Xhigh)
  4. 5353GPT-6 Astra (Low)
  5. 5252GPT-6.1 Sol (Low)
  6. 5252Llama 4 Maverick
  7. 5252Qwen3.8-Flash-Next
  8. 5151Granite 4.2 3B
  9. 5151GPT-6.1 Sol (Medium)
  10. 5050Qwen3.8 27B (Non-reasoning)
Data from Artificial Analysis

Latency

seconds to first token · #40 of 162
  1. 11Gemma 4 26B A4B (Non-reasoning)
  2. 11gpt-oss-20b (Low)
  3. 11NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)
  4. 11Ministral 3 14B
  5. 11Claude Sonnet 5.5 (Low)
  6. 11Llama 4 Maverick
  7. 11Nova 2.0 Pro Preview (Non-reasoning)
  8. 11Nova 2.0 Lite (Non-reasoning)
  9. 11NVIDIA Nemotron Nano 9B V2 (Non-reasoning)
  10. 1.11.1NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)
Data from Artificial Analysis

Price

$ per 1M tokens (3:1) · #70 of 169
  1. $0.350.35Llama 3.2 Instruct 11B (Vision)
  2. $0.350.35Qwen3 Next 80B A3B Instruct
  3. $0.350.35Reka Flash 3
  4. $0.380.38Mercury 2.5
  5. $0.390.39Trinity Large Thinking
  6. $0.420.42Llama 4 Maverick
  7. $0.430.43Qwen3 Omni 30B A3B (Reasoning)
  8. $0.430.43Qwen3 Omni 30B A3B Instruct
  9. $0.450.45Ling 3.1 Flash 1019
  10. $0.450.45Ling 3.1 Flash
Data from Artificial Analysis

Nearby models

  • North Mini CodeCohere9.9
  • K2-V2 (High)Institute of Foundation Models9.9
  • Qwen3 Next 80B A3B InstructAlibaba9.6
  • DiffusionGemma 26B A4BGoogle9.5
  • Gemma 4 12B (Non-reasoning)Google9.4
  • Qwen3 Coder NextAlibaba9.2
  • Motif-2-12.7B-ReasoningMotif Technologies9.2
  • Nova PremierAmazon9.2
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 3.3 Instruct 70BMeta7.7
  • Llama 3.1 Instruct 405BMeta7.3
  • Llama 4 ScoutMeta6.5
  • Llama 3.2 Instruct 90B (Vision)Meta6.4
Data from Artificial Analysis
HorizonVascend IDEOlympusTalosCoursesCommunityBenchmark
DiscordGitHubXLet’s talkLegalPrivacyCookiesData useSecurity
© 2026 Vascend Technologies · VAT IT04911550616
ascend