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

Claude Haiku 5.5 (Medium)

  • Anthropic
  • Proprietary
  • Reasoning

Intelligence

Intelligence Index

#59 of 266
  1. 3636DeepSeek V4 Pro 0813 (Max)
  2. 35.936Claude Sonnet 5.5 (Low)
  3. 35.235Agnes 2.5 Pro Beta
  4. 34.835DeepSeek V4 Flash Vision (Max)
  5. 34.635GPT-6 Luna (Xhigh)
  6. 34.535Claude Haiku 5.5 (Medium)
  7. 34.334GLM-5.3 (Low)
  8. 34.234GPT-5.6 Terra (High)
  9. 33.934JT-4.1 Flash 236B A21B (Reasoning)
  10. 33.734Qwen3.8 27B (Xhigh)
Data from Artificial Analysis

Evaluations

  • AA-Omniscience Accuracy34%#66
  • Humanity's Last Exam33.8%#72
  • Terminal-Bench 4.015.2%#52
  • AA-LCR77.3%#73
  • SciCode49%#68
  • CritPt12.9%#61
Claude Haiku 5.5 (Medium)Median
Data from Artificial Analysis

Speed and price

Speed

tokens per second · #30 of 162
  1. 186186gpt-oss-20b (Low)
  2. 186186Claude Haiku 5.5 (Xhigh)
  3. 183183Nova 2.0 Lite (Non-reasoning)
  4. 181181Claude Haiku 5.5 (High)
  5. 180180Nova 2.0 Lite (Medium)
  6. 179179Claude Haiku 5.5 (Medium)
  7. 178178Mistral Small 4 (Reasoning)
  8. 177177DeepSeek V4 Flash Vision (Max)
  9. 173173Mistral Small 4 (Non-reasoning)
  10. 173173Claude Haiku 5.5 (Low)
Data from Artificial Analysis

Latency

seconds to first token · #127 of 162
  1. 6.36.3Grok 4.7 (Low)
  2. 7.27.2o3
  3. 7.57.5Claude Haiku 5.5 (Low)
  4. 7.97.9Gemini 3.5 Flash-Lite
  5. 9.29.2Nova 2.0 Lite (Low)
  6. 9.710Claude Haiku 5.5 (Medium)
  7. 10.511Claude Sonnet 5.5 (High)
  8. 10.511GPT-6 Luna (High)
  9. 10.611Nova 2.0 Pro Preview (Low)
  10. 12.513Nova 2.0 Pro Preview (Medium)
Data from Artificial Analysis

Price

$ per 1M tokens (3:1) · #42 of 169
  1. $0.20.2Claude Haiku 5.5 (Max)
  2. $0.20.2Claude Haiku 5.5 (Xhigh)
  3. $0.20.2GPT-6 Luna (Max)
  4. $0.20.2Claude Haiku 5.5 (High)
  5. $0.20.2GPT-6 Luna (Xhigh)
  6. $0.20.2Claude Haiku 5.5 (Medium)
  7. $0.20.2GPT-6 Luna (High)
  8. $0.20.2GPT-6 Luna (Medium)
  9. $0.20.2Claude Haiku 5.5 (Low)
  10. $0.20.2GPT-6 Luna (Low)
Data from Artificial Analysis

Nearby models

  • DeepSeek V4 Pro 0813 (Max)DeepSeek36
  • Claude Sonnet 5.5 (Low)Anthropic35.9
  • Agnes 2.5 Pro BetaSapiens AI35.2
  • DeepSeek V4 Flash Vision (Max)DeepSeek34.8
  • GPT-6 Luna (Xhigh)OpenAI34.6
  • GLM-5.3 (Low)Z AI34.3
  • GPT-5.6 Terra (High)OpenAI34.2
  • JT-4.1 Flash 236B A21B (Reasoning)China Mobile33.9
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