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

Trinity Large Thinking

  • Arcee AI
  • Release · April 1, 2026
  • Open weights
  • Reasoning

Intelligence

Intelligence Index

#160 of 266
  1. 11.211Qwen3 Next 80B A3B (Reasoning)
  2. 11.111Granite 4.2 8B
  3. 11.111Ling 3.0 Tiny
  4. 11.111Nova 2.0 Omni (Low)
  5. 1111Mi:dm K 2.5 Pro
  6. 10.811Trinity Large Thinking
  7. 10.811G9v3-3B
  8. 10.811Qwen3.5 4B (Non-reasoning)
  9. 10.611INTELLECT-3 (Based on GLM-4.5-Air)
  10. 10.410Solar Open 100B (Reasoning)
Data from Artificial Analysis

Evaluations

  • AA-Omniscience Accuracy22.5%#103
  • Humanity's Last Exam15.9%#114
  • Terminal-Bench 4.00.5%#86
  • AA-LCR38%#162
  • SciCode40.6%#100
  • CritPt0.9%#106
  • GPQA Diamond75.2%#93
  • IFBench56.3%#50
  • τ²-Bench Telecom90.1%#13
  • τ²-Bench Banking5.8%#83
  • Terminal-Bench Hard22.7%#33
Trinity Large ThinkingMedian
Data from Artificial Analysis

Speed and price

Speed

tokens per second · #7 of 162
  1. 879879K2 Horizon 375B A23B
  2. 714714Mercury 2.5
  3. 446446Nemotron 3.5 Super VL
  4. 414414Gemini 3.5 Flash-Lite
  5. 363363Beam 1.0
  6. 353353Trinity Large Thinking
  7. 295295Nemotron 3.5 Lightning
  8. 290290Nova Micro
  9. 277277NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)
  10. 265265gpt-oss-120b (Low)
Data from Artificial Analysis

Latency

seconds to first token · #51 of 162
  1. 1.11.1Gemma 4 31B (Reasoning)
  2. 1.21.2Step 5 Preview
  3. 1.21.2Nemotron 3 Ultra 550B A55B (Reasoning)
  4. 1.21.2DeepSeek V4.1 Flash 1017 (Max)
  5. 1.31.3Quasar 438B (Max, Based on GLM-5.2)
  6. 1.31.3Trinity Large Thinking
  7. 1.31.3MiniMax-M3
  8. 1.31.3Llama 3.2 Instruct 11B (Vision)
  9. 1.41.4MiniMax-M3.1-Flash
  10. 1.41.4Claude Sonnet 5.5 (Medium)
Data from Artificial Analysis

Price

$ per 1M tokens (3:1) · #69 of 169
  1. $0.330.33Celeris-1
  2. $0.350.35Llama 3.2 Instruct 11B (Vision)
  3. $0.350.35Qwen3 Next 80B A3B Instruct
  4. $0.350.35Reka Flash 3
  5. $0.380.38Mercury 2.5
  6. $0.390.39Trinity Large Thinking
  7. $0.420.42Llama 4 Maverick
  8. $0.430.43Qwen3 Omni 30B A3B (Reasoning)
  9. $0.430.43Qwen3 Omni 30B A3B Instruct
  10. $0.450.45Ling 3.1 Flash 1019
Data from Artificial Analysis

Nearby models

  • Qwen3 Next 80B A3B (Reasoning)Alibaba11.2
  • Granite 4.2 8BIBM11.1
  • Ling 3.0 TinyInclusionAI11.1
  • Nova 2.0 Omni (Low)Amazon11.1
  • Mi:dm K 2.5 ProKorea Telecom11
  • G9v3-3BAI9Stars10.8
  • Qwen3.5 4B (Non-reasoning)Alibaba10.8
  • INTELLECT-3 (Based on GLM-4.5-Air)Prime Intellect10.6
Data from Artificial Analysis
HorizonVascend IDEOlympusTalosCoursesCommunityBenchmark
DiscordGitHubXLet’s talkLegalPrivacyCookiesData useSecurity
© 2026 Vascend Technologies · VAT IT04911550616
ascend