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

Gemma 4 26B A4B (Non-reasoning)

  • Google
  • Open weights
  • Non-reasoning

Intelligence

Intelligence Index

#135 of 266
  1. 13.413Nova 2.0 Lite (High)
  2. 13.413Apriel-v1.6-15B-Thinker
  3. 13.313Qwen3.5 9B (Non-reasoning)
  4. 13.213EXAONE 4.5 33B (Reasoning)
  5. 13.113Qwen3.5 4B (Reasoning)
  6. 13.113Gemma 4 26B A4B (Non-reasoning)
  7. 13.113Command A+
  8. 12.913Nemotron 3.5 Lightning
  9. 12.813Nova 2.0 Pro Preview (Low)
  10. 12.713Granite 4.2 30B
Data from Artificial Analysis

Evaluations

  • AA-Omniscience Accuracy15.5%#167
  • Humanity's Last Exam11.5%#135
  • AA-LCR42.3%#154
  • CritPt0%#143
  • MMMU-Pro66.7%#70
  • GPQA Diamond71.4%#112
  • IFBench45.4%#69
  • τ²-Bench Telecom40.4%#76
  • Terminal-Bench Hard25%#26
Gemma 4 26B A4B (Non-reasoning)Median
Data from Artificial Analysis

Speed and price

Speed

tokens per second · #82 of 162
  1. 114114Agnes 2.5 Pro Beta
  2. 113113MiniMax-M3.1-Flash
  3. 112112Solar Mini 4
  4. 109109Mistral Large 4 Preview
  5. 108108Claude Sonnet 5.5 (Xhigh)
  6. 108108Gemma 4 26B A4B (Non-reasoning)
  7. 106106Claude Sonnet 5.5 (Medium)
  8. 106106Claude Sonnet 5.5 (High)
  9. 105105Claude Sonnet 5.5 (Low)
  10. 105105Muse Glimmer (High)
Data from Artificial Analysis

Latency

seconds to first token · #35 of 162
  1. 0.90.9Gemma 4 E4B (Reasoning)
  2. 0.90.9Gemma 4 26B A4B (Reasoning)
  3. 0.90.9Qwen3.5 4B (Reasoning)
  4. 0.90.9Qwen3 Coder Next
  5. 0.90.9Mistral Small 4 (Non-reasoning)
  6. 11Gemma 4 26B A4B (Non-reasoning)
  7. 11gpt-oss-20b (Low)
  8. 11NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)
  9. 11Ministral 3 14B
  10. 11Claude Sonnet 5.5 (Low)
Data from Artificial Analysis

Price

$ per 1M tokens (3:1) · #35 of 169
  1. $0.150.15Qwen3.5 9B (Reasoning)
  2. $0.160.16Gemma 4 26B A4B (Reasoning)
  3. $0.170.17Quasar 438B (Max, Based on GLM-5.2)
  4. $0.180.18MiMo-V2.6-Flash
  5. $0.180.18Solar Mini 4
  6. $0.190.19Gemma 4 26B A4B (Non-reasoning)
  7. $0.190.19Qwen3.5 9B (Non-reasoning)
  8. $0.20.2Claude Haiku 5.5 (Max)
  9. $0.20.2Claude Haiku 5.5 (Xhigh)
  10. $0.20.2GPT-6 Luna (Max)
Data from Artificial Analysis

Nearby models

  • Nova 2.0 Lite (High)Amazon13.4
  • Apriel-v1.6-15B-ThinkerServiceNow13.4
  • Qwen3.5 9B (Non-reasoning)Alibaba13.3
  • EXAONE 4.5 33B (Reasoning)LG AI Research13.2
  • Qwen3.5 4B (Reasoning)Alibaba13.1
  • Command A+Cohere13.1
  • Nemotron 3.5 LightningNVIDIA12.9
  • Nova 2.0 Pro Preview (Low)Amazon12.8
Data from Artificial Analysis

Same lab

  • Gemini 4 Argon (High)Google52.6
  • Gemini 3.8 Flash (High)Google40.9
  • Gemini 3.8 Flash (Medium)Google39.8
  • Gemini 3.8 Flash (Low)Google33.5
  • Gemini 3.1 Pro PreviewGoogle29.7
  • Gemini 3.5 Flash-LiteGoogle22.2
  • Gemma 4 26B A4B (Reasoning)Google16.7
  • Gemma 4 31B (Reasoning)Google14.7
Data from Artificial Analysis
HorizonVascend IDEOlympusTalosCoursesCommunityBenchmark
DiscordGitHubXLet’s talkLegalPrivacyCookiesData useSecurity
© 2026 Vascend Technologies · VAT IT04911550616
ascend