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

Muse Wonder (Max)

  • Meta
  • Release · October 12, 2026
  • Proprietary
  • Reasoning

Intelligence

Intelligence Index

#12 of 266
  1. 53.453Claude Fable 5.1 (Max)
  2. 53.253Claude Fable 5.1 (Xhigh)
  3. 52.753GPT-6 Astra (Max)
  4. 52.653Gemini 4 Argon (High)
  5. 52.452GPT-6 Astra (Xhigh)
  6. 52.452Muse Wonder (Max)
  7. 51.952Claude Sonnet 5.5 (Xhigh)
  8. 51.852GPT-6.1 Sol (Max)
  9. 51.251Claude Opus 5.5 (Medium)
  10. 51.251Claude Fable 5.1 (High)
Data from Artificial Analysis

Evaluations

  • AA-Briefcase1,659#6
  • AA-Omniscience Accuracy41.1%#54
  • AA-Omniscience Non-Hallucination73.5%#5
  • AutomationBench-AA68.1%#8
  • GDPval-AA1,770#5
  • Humanity's Last Exam50.1%#20
  • GDP.pdf30.6%#5
  • Terminal-Bench 4.052%#16
  • AA-LCR80.7%#37
  • SciCode60.3%#11
  • CritPt28.3%#19
  • Terminal-Bench-Science25.7%#9
  • FrontierCode46.5%#6
  • Harvey LAB-AA10%#2
  • MLCR-AA22.2%#9
  • PersonalityBench: Expressiveness87.3#5
  • PersonalityBench: Organization89.8#4
  • PersonalityBench: Transparency56.8#14
  • PersonalityBench: Slop54.3#10
  • PersonalityBench: Informativeness94.9#2
  • PersonalityBench: Warmth100#1
  • PersonalityBench: Conviction77.2#7
  • PersonalityBench: Imagination89.8#4
Muse Wonder (Max)Median
Data from Artificial Analysis

Cost per task

Cost per task

$ per Intelligence Index task · #20 of 24
  1. $1.991.99Gemini 4 Argon (High)
  2. $2.012.01GLM-5.3 (Max)
  3. $2.112.11Kimi K3.1 Pro
  4. $3.263.26GPT-6 Astra (Max)
  5. $3.743.74Grok 4.7 (Xhigh)
  6. $4.544.54Muse Wonder (Max)
  7. $5.415.41Qwen3.8 Max (0902)
  8. $5.465.46Claude Sonnet 5.5 (Max)
  9. $5.985.98Claude Opus 5.5 (Max)
  10. $7.637.63Claude Fable 5.1 (Max)
Data from Artificial Analysis

Time per task

seconds per task · #7 of 26
  1. 5757Beam 1.0
  2. 9696Nemotron 3.5 Super VL
  3. 165165Inkling (Xhigh)
  4. 263263Step 5 Preview
  5. 284284Muse Spark Open (Xhigh)
  6. 341341Muse Wonder (Max)
  7. 364364GPT-6 Luna (Max)
  8. 396396DeepSeek V4.1 Flash 1017 (Max)
  9. 412412GPT-6 Astra (Max)
  10. 428428Claude Haiku 5.5 (Max)
Data from Artificial Analysis

Tokens per task

output tokens per task · #10 of 27
  1. 40.4K40KMuse Spark Open (Xhigh)
  2. 49.2K49KNemotron 3.5 Super VL
  3. 50K50KGPT-6 Luna (Max)
  4. 51.5K52KK2 Horizon 375B A23B
  5. 53.8K54KMuse Wonder Full (Max)
  6. 54.5K55KMuse Wonder (Max)
  7. 55.2K55KKimi K3.1 Pro
  8. 61.6K62KGemini 4 Argon (High)
  9. 64.1K64KStep 5 Preview
  10. 64.3K64KMiMo-V2.6-Pro
Data from Artificial Analysis

Speed and price

Speed

tokens per second · #41 of 162
  1. 173173Nova 2.0 Lite (Low)
  2. 169169DeepSeek V4.1 Flash 1017 (Max)
  3. 168168NVIDIA Nemotron Nano 9B V2 (Non-reasoning)
  4. 166166Command A+
  5. 162162Mistral Medium 3.5
  6. 162162Muse Wonder (Max)
  7. 159159Quasar 438B (Max, Based on GLM-5.2)
  8. 158158Nemotron 3 Ultra 550B A55B (Reasoning)
  9. 152152GPT-5.5 Instant (June 2026)
  10. 152152o3
Data from Artificial Analysis

Latency

seconds to first token · #143 of 162
  1. 20.621Gemini 3.1 Pro Preview
  2. 20.921Grok 4.7 (High)
  3. 2525Claude Haiku 5.5 (High)
  4. 27.327Gemini 3.8 Flash (High)
  5. 27.327Claude Sonnet 5.5 (Xhigh)
  6. 27.528Muse Wonder (Max)
  7. 30.330Claude Opus 5.5 (High)
  8. 36.136GPT-6.1 Sol (High)
  9. 40.340Grok 4.7 (Xhigh)
  10. 40.741GPT-6 Astra (High)
Data from Artificial Analysis

Price

$ per 1M tokens (3:1) · #156 of 169
  1. $4.54.5GPT-5.6 Terra (Non-reasoning)
  2. $4.814.81GPT-5.3 Codex (Xhigh)
  3. $88Claude Opus 5.5 (Max)
  4. $88Claude Opus 5.5 (Xhigh)
  5. $88Claude Opus 5.5 (High)
  6. $88Muse Wonder (Max)
  7. $88Claude Opus 5.5 (Medium)
  8. $88Claude Opus 5.5 (Low)
  9. $11.25$11GPT-5.5 Instant (June 2026)
  10. $2020Claude Fable 5.1 (Max)
Data from Artificial Analysis

Nearby models

  • Claude Fable 5.1 (Max)Anthropic53.4
  • Claude Fable 5.1 (Xhigh)Anthropic53.2
  • GPT-6 Astra (Max)OpenAI52.7
  • Gemini 4 Argon (High)Google52.6
  • GPT-6 Astra (Xhigh)OpenAI52.4
  • Claude Sonnet 5.5 (Xhigh)Anthropic51.9
  • GPT-6.1 Sol (Max)OpenAI51.8
  • Claude Opus 5.5 (Medium)Anthropic51.2
Data from Artificial Analysis

Same lab

  • Muse Wonder Full (Max)Meta55.8
  • 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 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