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

Gemma 4 26B A4B (Reasoning)

  • Google
  • Release · April 2, 2026
  • Open weights
  • Reasoning

Intelligence

Intelligence Index

#118 of 266
  1. 18.418Qwen3.5 397B A17B (Reasoning)
  2. 18.218Qwen3.6 35B A3B (Reasoning)
  3. 17.718Qwen3.5 122B A10B (Non-reasoning)
  4. 17.518Muse Glimmer (High)
  5. 16.917Doubao Seed Code
  6. 16.717Gemma 4 26B A4B (Reasoning)
  7. 16.617Ring-2.6-1T
  8. 15.616K2 Horizon 3.7B
  9. 15.616Qwen3.5 122B A10B (Reasoning)
  10. 15.215Qwen3.6 35B A3B (Non-reasoning)
Data from Artificial Analysis

Evaluations

  • AA-Omniscience Accuracy19.1%#119
  • Humanity's Last Exam19.3%#105
  • AA-LCR65.7%#114
  • SciCode40.1%#103
  • CritPt0%#143
  • MMMU-Pro69.3%#65
  • GPQA Diamond79.2%#73
  • IFBench72.5%#14
  • τ²-Bench Telecom43.6%#72
  • τ²-Bench Banking12%#66
  • Terminal-Bench Hard13.6%#48
Gemma 4 26B A4B (Reasoning)Median
Data from Artificial Analysis

Speed and price

Speed

tokens per second · #99 of 162
  1. 9696Claude Opus 5.5 (Max)
  2. 9494Qwen3 Coder Next
  3. 9393Grok 4.7 (Xhigh)
  4. 9292GPT-6 Luna (Medium)
  5. 9191GLM-5.3 (Low)
  6. 9191Gemma 4 26B A4B (Reasoning)
  7. 8989Llama 3.3 Instruct 70B
  8. 8888Reka Flash 3
  9. 8686Grok 4.7 (High)
  10. 8383Claude Opus 5.5 (Medium)
Data from Artificial Analysis

Latency

seconds to first token · #31 of 162
  1. 0.90.9GPT-6 Luna (Non-reasoning)
  2. 0.90.9GPT-5.5 Instant (June 2026)
  3. 0.90.9Qwen3.5 9B (Non-reasoning)
  4. 0.90.9Qwen3.5 4B (Non-reasoning)
  5. 0.90.9Gemma 4 E4B (Reasoning)
  6. 0.90.9Gemma 4 26B A4B (Reasoning)
  7. 0.90.9Qwen3.5 4B (Reasoning)
  8. 0.90.9Qwen3 Coder Next
  9. 0.90.9Mistral Small 4 (Non-reasoning)
  10. 11Gemma 4 26B A4B (Non-reasoning)
Data from Artificial Analysis

Price

$ per 1M tokens (3:1) · #31 of 169
  1. $0.150.15Agnes 2.5 Pro Beta
  2. $0.150.15Gemma 4 12B (Reasoning)
  3. $0.150.15Gemma 4 12B (Non-reasoning)
  4. $0.150.15Ministral 3 8B
  5. $0.150.15Qwen3.5 9B (Reasoning)
  6. $0.160.16Gemma 4 26B A4B (Reasoning)
  7. $0.170.17Quasar 438B (Max, Based on GLM-5.2)
  8. $0.180.18MiMo-V2.6-Flash
  9. $0.180.18Solar Mini 4
  10. $0.190.19Gemma 4 26B A4B (Non-reasoning)
Data from Artificial Analysis

Nearby models

  • Qwen3.5 397B A17B (Reasoning)Alibaba18.4
  • Qwen3.6 35B A3B (Reasoning)Alibaba18.2
  • Qwen3.5 122B A10B (Non-reasoning)Alibaba17.7
  • Muse Glimmer (High)Meta17.5
  • Doubao Seed CodeByteDance Seed16.9
  • Ring-2.6-1TInclusionAI16.6
  • K2 Horizon 3.7BInstitute of Foundation Models15.6
  • Qwen3.5 122B A10B (Reasoning)Alibaba15.6
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 31B (Reasoning)Google14.7
  • Gemma 4 12B (Reasoning)Google14.2
Data from Artificial Analysis
HorizonVascend IDEOlympusTalosCoursesCommunityBenchmark
DiscordGitHubXLet’s talkLegalPrivacyCookiesData useSecurity
© 2026 Vascend Technologies · VAT IT04911550616
ascend