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

Claude Haiku 5.5 (Low)

  • Anthropic
  • Proprietary
  • Reasoning

Intelligence

Intelligence Index

#73 of 266
  1. 30.531K2 Horizon 375B A23B
  2. 30.330Beam 1.0
  3. 30.130GPT-5.6 Terra (Medium)
  4. 29.930GPT-6 Luna (Medium)
  5. 29.730Gemini 3.1 Pro Preview
  6. 29.530Claude Haiku 5.5 (Low)
  7. 29.229MiniMax-M3
  8. 28.228Nex-N2-Pro (Based on Qwen3.5-397B-A17B)
  9. 27.628Qwen3.8 27B (Medium)
  10. 27.528GPT-5.6 Terra (Low)
Data from Artificial Analysis

Evaluations

  • AA-Omniscience Accuracy33.3%#69
  • Humanity's Last Exam27%#89
  • Terminal-Bench 4.012.6%#54
  • AA-LCR72%#95
  • SciCode49.2%#66
  • CritPt9.1%#73
Claude Haiku 5.5 (Low)Median
Data from Artificial Analysis

Speed and price

Speed

tokens per second · #34 of 162
  1. 180180Nova 2.0 Lite (Medium)
  2. 179179Claude Haiku 5.5 (Medium)
  3. 178178Mistral Small 4 (Reasoning)
  4. 177177DeepSeek V4 Flash Vision (Max)
  5. 173173Mistral Small 4 (Non-reasoning)
  6. 173173Claude Haiku 5.5 (Low)
  7. 173173gpt-oss-20b (High)
  8. 173173Nova 2.0 Lite (Low)
  9. 169169DeepSeek V4.1 Flash 1017 (Max)
  10. 168168NVIDIA Nemotron Nano 9B V2 (Non-reasoning)
Data from Artificial Analysis

Latency

seconds to first token · #124 of 162
  1. 5.15.1GPT-6 Astra (Medium)
  2. 5.25.2Claude Fable 5.1 (Medium)
  3. 6.26.2Claude Opus 5.5 (Low)
  4. 6.36.3Grok 4.7 (Low)
  5. 7.27.2o3
  6. 7.57.5Claude Haiku 5.5 (Low)
  7. 7.97.9Gemini 3.5 Flash-Lite
  8. 9.29.2Nova 2.0 Lite (Low)
  9. 9.710Claude Haiku 5.5 (Medium)
  10. 10.511Claude Sonnet 5.5 (High)
Data from Artificial Analysis

Price

$ per 1M tokens (3:1) · #45 of 169
  1. $0.20.2Claude Haiku 5.5 (High)
  2. $0.20.2GPT-6 Luna (Xhigh)
  3. $0.20.2Claude Haiku 5.5 (Medium)
  4. $0.20.2GPT-6 Luna (High)
  5. $0.20.2GPT-6 Luna (Medium)
  6. $0.20.2Claude Haiku 5.5 (Low)
  7. $0.20.2GPT-6 Luna (Low)
  8. $0.20.2GPT-6 Luna (Non-reasoning)
  9. $0.20.2Ministral 3 14B
  10. $0.220.22Phi-4
Data from Artificial Analysis

Nearby models

  • K2 Horizon 375B A23BInstitute of Foundation Models30.5
  • Beam 1.0Reflection30.3
  • GPT-5.6 Terra (Medium)OpenAI30.1
  • GPT-6 Luna (Medium)OpenAI29.9
  • Gemini 3.1 Pro PreviewGoogle29.7
  • MiniMax-M3MiniMax29.2
  • Nex-N2-Pro (Based on Qwen3.5-397B-A17B)Nex AGI28.2
  • Qwen3.8 27B (Medium)Alibaba27.6
Data from Artificial Analysis

Same lab

  • Claude Opus 5.5 (Max)Anthropic57.6
  • Claude Opus 5.5 (Xhigh)Anthropic56
  • Claude Sonnet 5.5 (Max)Anthropic56
  • Claude Opus 5.5 (High)Anthropic53.6
  • Claude Fable 5.1 (Max)Anthropic53.4
  • Claude Fable 5.1 (Xhigh)Anthropic53.2
  • Claude Sonnet 5.5 (Xhigh)Anthropic51.9
  • Claude Opus 5.5 (Medium)Anthropic51.2
Data from Artificial Analysis
HorizonVascend IDEOlympusTalosCoursesCommunityBenchmark
DiscordGitHubXLet’s talkLegalPrivacyCookiesData useSecurity
© 2026 Vascend Technologies · VAT IT04911550616
ascend