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

Gemma 4 E4B (Non-reasoning)

  • Google
  • Open weights
  • Non-reasoning

Intelligence

Intelligence Index

#203 of 266
  1. 7.77.7Step3 VL 10B
  2. 7.77.7Llama 3.3 Instruct 70B
  3. 7.57.5Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)
  4. 7.57.5ERNIE 4.5 300B A47B
  5. 7.57.5NVIDIA Nemotron Nano 12B v2 VL (Reasoning)
  6. 7.57.5Gemma 4 E4B (Non-reasoning)
  7. 7.57.5Hermes 4 - Llama-3.1 405B (Reasoning)
  8. 7.47.4Hermes 4 - Llama-3.1 405B (Non-reasoning)
  9. 7.47.4NVIDIA Nemotron Nano 9B V2 (Reasoning)
  10. 7.37.3K2-V2 (Low)
Data from Artificial Analysis

Evaluations

  • AA-Omniscience Accuracy8.3%#234
  • Humanity's Last Exam4.8%#220
  • AA-LCR24%#185
  • CritPt0.3%#117
  • MMMU-Pro51.2%#101
  • GPQA Diamond55%#159
  • IFBench40.5%#86
  • τ²-Bench Telecom26%#91
  • Terminal-Bench Hard7.6%#68
Gemma 4 E4B (Non-reasoning)Median
Data from Artificial Analysis

Speed and price

Speed

tokens per second · #152 of 162
  1. 4848Qwen3.8 27B (Medium)
  2. 4848Granite 4.2 30B
  3. 4646Phi-4 Mini Instruct
  4. 4545Gemma 4 E4B (Reasoning)
  5. 4545Qwen3.8 27B (Xhigh)
  6. 4545Gemma 4 E4B (Non-reasoning)
  7. 4343Hermes 4 - Llama-3.1 405B (Non-reasoning)
  8. 4343Hermes 4 - Llama-3.1 405B (Reasoning)
  9. 4141Qwen3.8 2.4T A95B
  10. 4040Qwen3.8 Max (0902)
Data from Artificial Analysis

Latency

seconds to first token · #18 of 162
  1. 0.80.8gpt-oss-20b (High)
  2. 0.80.8Llama 4 Scout
  3. 0.80.8Muse Spark Open (Xhigh)
  4. 0.80.8gpt-oss-120b (High)
  5. 0.80.8Granite 4.2 8B
  6. 0.80.8Gemma 4 E4B (Non-reasoning)
  7. 0.80.8NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)
  8. 0.80.8Nova Micro
  9. 0.80.8Granite 4.2 30B
  10. 0.80.8Nemotron 3 Nano Omni 30B A3B Reasoning
Data from Artificial Analysis

Price

$ per 1M tokens (3:1) · #8 of 169
  1. $00Command A+
  2. $00Ling 3.0 Tiny
  3. $00North Mini Code
  4. $00Tiny Aya Global
  5. $0.040.04Gemma 4 E4B (Reasoning)
  6. $0.040.04Gemma 4 E4B (Non-reasoning)
  7. $0.050.05Granite 4.2 3B
  8. $0.060.06Qwen3.5 4B (Reasoning)
  9. $0.060.06Qwen3.5 4B (Non-reasoning)
  10. $0.060.06Nova Micro
Data from Artificial Analysis

Nearby models

  • Step3 VL 10BStepFun7.7
  • Llama 3.3 Instruct 70BMeta7.7
  • Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)NVIDIA7.5
  • ERNIE 4.5 300B A47BBaidu7.5
  • NVIDIA Nemotron Nano 12B v2 VL (Reasoning)NVIDIA7.5
  • Hermes 4 - Llama-3.1 405B (Reasoning)Nous Research7.5
  • Hermes 4 - Llama-3.1 405B (Non-reasoning)Nous Research7.4
  • NVIDIA Nemotron Nano 9B V2 (Reasoning)NVIDIA7.4
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