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

Solar Open 100B (Reasoning)

  • Upstage
  • Open weights
  • Reasoning

Intelligence

Intelligence Index

#164 of 266
  1. 1111Mi:dm K 2.5 Pro
  2. 10.811Trinity Large Thinking
  3. 10.811G9v3-3B
  4. 10.811Qwen3.5 4B (Non-reasoning)
  5. 10.611INTELLECT-3 (Based on GLM-4.5-Air)
  6. 10.410Solar Open 100B (Reasoning)
  7. 10.310Nemotron 3 Nano Omni 30B A3B Reasoning
  8. 10.210gpt-oss-120b (Low)
  9. 1010Nova 2.0 Pro Preview (Non-reasoning)
  10. 1010gpt-oss-20b (Low)
Data from Artificial Analysis

Evaluations

  • AA-Omniscience Accuracy18.5%#131
  • Humanity's Last Exam10.4%#152
  • AA-LCR41%#156
  • CritPt0%#143
  • GPQA Diamond65.7%#132
  • IFBench57.7%#47
  • τ²-Bench Telecom48.3%#65
  • Terminal-Bench Hard2.3%#100
Solar Open 100B (Reasoning)Median
Data from Artificial Analysis

Nearby models

  • Mi:dm K 2.5 ProKorea Telecom11
  • Trinity Large ThinkingArcee AI10.8
  • G9v3-3BAI9Stars10.8
  • Qwen3.5 4B (Non-reasoning)Alibaba10.8
  • INTELLECT-3 (Based on GLM-4.5-Air)Prime Intellect10.6
  • Nemotron 3 Nano Omni 30B A3B ReasoningNVIDIA10.3
  • gpt-oss-120b (Low)OpenAI10.2
  • Nova 2.0 Pro Preview (Non-reasoning)Amazon10
Data from Artificial Analysis

Same lab

  • Solar Pro 4Upstage26.6
  • Solar Open2 250BUpstage24.7
  • Solar Mini 4Upstage24.1
Data from Artificial Analysis
HorizonVascend IDEOlympusTalosCoursesCommunityBenchmark
DiscordGitHubXLet’s talkLegalPrivacyCookiesData useSecurity
© 2026 Vascend Technologies · VAT IT04911550616
ascend