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

Apertus 8B Instruct

  • Swiss AI Initiative
  • Release · September 2, 2025
  • Open weights
  • Non-reasoning

Intelligence

Intelligence Index

#264 of 266
  1. 5.15.1Granite 4.0 Micro
  2. 55Molmo2-8B
  3. 4.84.8Granite 4.0 H 350M
  4. 4.84.8Granite 4.0 350M
  5. 4.84.8NVIDIA Nemotron 3 Nano 4B
  6. 4.84.8Ministral 3 3B
  7. 4.84.8Tiny Aya Global
  8. 4.84.8Apertus 8B Instruct
  9. 4.84.8LFM2.5-VL-1.6B
  10. 33K2 Horizon 0.9B
Data from Artificial Analysis

Evaluations

  • AA-Omniscience Accuracy9.7%#222
  • Humanity's Last Exam5%#210
  • AA-LCR0%#229
  • CritPt0%#143
  • GPQA Diamond25.6%#210
  • IFBench22.4%#145
  • τ²-Bench Telecom11.4%#135
  • Terminal-Bench Hard0%#121
Apertus 8B InstructMedian
Data from Artificial Analysis

Speed and price

Speed

tokens per second · #51 of 162
  1. 151151Muse Spark Open (Xhigh)
  2. 147147Qwen3.6 35B A3B (Non-reasoning)
  3. 143143Qwen3.5 122B A10B (Non-reasoning)
  4. 140140GPT-6 Luna (Max)
  5. 137137Gemini 3.8 Flash (High)
  6. 136136Apertus 8B Instruct
  7. 134134Claude Sonnet 5.5 (Max)
  8. 133133Qwen3 Next 80B A3B Instruct
  9. 132132Gemini 3.1 Pro Preview
  10. 131131Qwen3.6 35B A3B (Reasoning)
Data from Artificial Analysis

Latency

seconds to first token · #110 of 162
  1. 2.82.8GLM-5.3-Flash
  2. 2.92.9Qwen3.8 2.4T A95B
  3. 33GLM-5.3 (Low)
  4. 3.13.1Kimi K3.1 Pro
  5. 3.13.1MiMo-V2.6-Pro
  6. 3.53.5Apertus 8B Instruct
  7. 3.63.6Mercury 2.5
  8. 3.73.7Ring-2.6-1T
  9. 3.83.8MiMo-V2.6-Flash
  10. 3.93.9Qwen3.8 27B (Xhigh)
Data from Artificial Analysis

Price

$ per 1M tokens (3:1) · #22 of 169
  1. $0.090.09NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)
  2. $0.090.09gpt-oss-20b (High)
  3. $0.10.1Nemotron 3.5 Lightning
  4. $0.10.1Ministral 3 3B
  5. $0.110.11Granite 4.2 8B
  6. $0.130.13Apertus 8B Instruct
  7. $0.130.13gpt-oss-20b (Low)
  8. $0.130.13Phi-4 Mini Instruct
  9. $0.140.14Phi-4 Multimodal Instruct
  10. $0.150.15Agnes 2.5 Pro Beta
Data from Artificial Analysis

Nearby models

  • Granite 4.0 MicroIBM5.1
  • Molmo2-8BAllen Institute for AI5
  • Granite 4.0 H 350MIBM4.8
  • Granite 4.0 350MIBM4.8
  • NVIDIA Nemotron 3 Nano 4BNVIDIA4.8
  • Ministral 3 3BMistral4.8
  • Tiny Aya GlobalCohere4.8
  • LFM2.5-VL-1.6BLiquid AI4.8
Data from Artificial Analysis

Same lab

  • Apertus 70B InstructSwiss AI Initiative5.1
Data from Artificial Analysis
HorizonVascend IDEOlympusTalosCoursesCommunityBenchmark
DiscordGitHubXLet’s talkLegalPrivacyCookiesData useSecurity
© 2026 Vascend Technologies · VAT IT04911550616
ascend