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

o3

  • OpenAI
  • Release · April 16, 2025
  • Proprietary
  • Reasoning

Intelligence

Intelligence Index

#107 of 266
  1. 21.421Nemotron 3.5 Bolt 74B-A9B
  2. 20.821GPT-5.6 Terra (Non-reasoning)
  3. 20.621K2 Horizon 7B
  4. 20.420Qwen3.5 Omni Plus
  5. 20.420DeepSeek V4 Pro 0813 (Non-reasoning)
  6. 20.220o3
  7. 20.220Qwen3.8 27B (Non-reasoning)
  8. 19.720K-EXAONE 2.0 0803
  9. 19.119LongCat 2.0
  10. 18.719JT-35B-Flash
Data from Artificial Analysis

Evaluations

  • AA-Omniscience Accuracy38.6%#58
  • Humanity's Last Exam20.1%#101
  • AA-LCR74.7%#87
  • CritPt1.1%#103
  • MMMU-Pro70.1%#62
  • GPQA Diamond82.7%#61
  • IFBench71.4%#15
  • τ²-Bench Telecom80.7%#37
  • Terminal-Bench Hard37.1%#12
o3Median
Data from Artificial Analysis

Speed and price

Speed

tokens per second · #45 of 162
  1. 162162Mistral Medium 3.5
  2. 162162Muse Wonder (Max)
  3. 159159Quasar 438B (Max, Based on GLM-5.2)
  4. 158158Nemotron 3 Ultra 550B A55B (Reasoning)
  5. 152152GPT-5.5 Instant (June 2026)
  6. 152152o3
  7. 151151Muse Spark Open (Xhigh)
  8. 147147Qwen3.6 35B A3B (Non-reasoning)
  9. 143143Qwen3.5 122B A10B (Non-reasoning)
  10. 140140GPT-6 Luna (Max)
Data from Artificial Analysis

Latency

seconds to first token · #123 of 162
  1. 44GPT-6.1 Sol (Medium)
  2. 5.15.1GPT-6 Astra (Medium)
  3. 5.25.2Claude Fable 5.1 (Medium)
  4. 6.26.2Claude Opus 5.5 (Low)
  5. 6.36.3Grok 4.7 (Low)
  6. 7.27.2o3
  7. 7.57.5Claude Haiku 5.5 (Low)
  8. 7.97.9Gemini 3.5 Flash-Lite
  9. 9.29.2Nova 2.0 Lite (Low)
  10. 9.710Claude Haiku 5.5 (Medium)
Data from Artificial Analysis

Price

$ per 1M tokens (3:1) · #131 of 169
  1. $33Qwen3.8 2.4T A95B
  2. $33Mistral Medium 3.5
  3. $3.443.44Nova 2.0 Pro Preview (Medium)
  4. $3.443.44Nova 2.0 Pro Preview (Low)
  5. $3.443.44Nova 2.0 Pro Preview (Non-reasoning)
  6. $3.53.5o3
  7. $44Claude Sonnet 5.5 (Max)
  8. $44Kimi K3.1 Pro
  9. $44Gemini 4 Argon (High)
  10. $44Claude Sonnet 5.5 (Xhigh)
Data from Artificial Analysis

Nearby models

  • Nemotron 3.5 Bolt 74B-A9BNVIDIA21.4
  • GPT-5.6 Terra (Non-reasoning)OpenAI20.8
  • K2 Horizon 7BInstitute of Foundation Models20.6
  • Qwen3.5 Omni PlusAlibaba20.4
  • DeepSeek V4 Pro 0813 (Non-reasoning)DeepSeek20.4
  • Qwen3.8 27B (Non-reasoning)Alibaba20.2
  • K-EXAONE 2.0 0803LG AI Research19.7
  • LongCat 2.0LongCat19.1
Data from Artificial Analysis

Same lab

  • GPT-6 Astra (Max)OpenAI52.7
  • GPT-6 Astra (Xhigh)OpenAI52.4
  • GPT-6.1 Sol (Max)OpenAI51.8
  • GPT-6.1 Sol (Xhigh)OpenAI51
  • GPT-6 Astra (High)OpenAI50.9
  • GPT-6.1 Sol (High)OpenAI50.2
  • GPT-6 Astra (Medium)OpenAI49.6
  • GPT-6.1 Sol (Medium)OpenAI47.8
Data from Artificial Analysis
HorizonVascend IDEOlympusTalosCoursesCommunityBenchmark
DiscordGitHubXLet’s talkLegalPrivacyCookiesData useSecurity
© 2026 Vascend Technologies · VAT IT04911550616
ascend