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

Gemma 4 31B (Non-reasoning)

  • Google
  • Open weights
  • Non-reasoning

Intelligence

Intelligence Index

#128 of 266
  1. 14.715Gemma 4 31B (Reasoning)
  2. 14.314ERNIE 5.0 Thinking Preview
  3. 14.214Nova 2.0 Pro Preview (Medium)
  4. 14.214Mistral Medium 3.5
  5. 14.214Gemma 4 12B (Reasoning)
  6. 13.914Gemma 4 31B (Non-reasoning)
  7. 13.614Nova 2.0 Omni (Medium)
  8. 13.413Nova 2.0 Lite (High)
  9. 13.413Apriel-v1.6-15B-Thinker
  10. 13.313Qwen3.5 9B (Non-reasoning)
Data from Artificial Analysis

Evaluations

  • AA-Omniscience Accuracy16.6%#155
  • Humanity's Last Exam11.8%#132
  • AA-LCR46.7%#150
  • CritPt0%#143
  • MMMU-Pro70.4%#60
  • GPQA Diamond76.3%#83
  • IFBench53.5%#55
  • τ²-Bench Telecom65.5%#54
  • τ²-Bench Banking8.9%#71
  • Terminal-Bench Hard30.3%#20
Gemma 4 31B (Non-reasoning)Median
Data from Artificial Analysis

Speed and price

Speed

tokens per second · #133 of 162
  1. 5757Claude Fable 5.1 (Low)
  2. 5757MiMo-V2.6-Pro
  3. 5757GPT-6 Astra (High)
  4. 5656Qwen3.7 Plus
  5. 5656MiMo-V2.6-Flash
  6. 5555Gemma 4 31B (Non-reasoning)
  7. 5555Claude Fable 5.1 (Medium)
  8. 5454Granite 4.2 8B
  9. 5353GPT-6.1 Sol (High)
  10. 5353GPT-6 Astra (Medium)
Data from Artificial Analysis

Latency

seconds to first token · #73 of 162
  1. 1.81.8Mistral Large 4 Preview
  2. 1.81.8Inkling (Xhigh)
  3. 1.81.8Qwen3.5 Omni Flash
  4. 1.81.8Command A
  5. 1.81.8Ling 3.1 Flash
  6. 1.81.8Gemma 4 31B (Non-reasoning)
  7. 1.81.8Qwen3 Omni 30B A3B Instruct
  8. 1.91.9Solar Mini 4
  9. 1.91.9Qwen3 Omni 30B A3B (Reasoning)
  10. 1.91.9Qwen3.5 9B (Reasoning)
Data from Artificial Analysis

Price

$ per 1M tokens (3:1) · #50 of 169
  1. $0.20.2Claude Haiku 5.5 (Low)
  2. $0.20.2GPT-6 Luna (Low)
  3. $0.20.2GPT-6 Luna (Non-reasoning)
  4. $0.20.2Ministral 3 14B
  5. $0.220.22Phi-4
  6. $0.220.22Gemma 4 31B (Non-reasoning)
  7. $0.230.23Qwen3.8-Flash-Next
  8. $0.240.24GLM-5.3-Flash
  9. $0.240.24Hy3
  10. $0.240.24gpt-oss-120b (Low)
Data from Artificial Analysis

Nearby models

  • Gemma 4 31B (Reasoning)Google14.7
  • ERNIE 5.0 Thinking PreviewBaidu14.3
  • Nova 2.0 Pro Preview (Medium)Amazon14.2
  • Mistral Medium 3.5Mistral14.2
  • Gemma 4 12B (Reasoning)Google14.2
  • Nova 2.0 Omni (Medium)Amazon13.6
  • Nova 2.0 Lite (High)Amazon13.4
  • Apriel-v1.6-15B-ThinkerServiceNow13.4
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 26B A4B (Non-reasoning)Google13.1
Data from Artificial Analysis
HorizonVascend IDEOlympusTalosCoursesCommunityBenchmark
DiscordGitHubXLet’s talkLegalPrivacyCookiesData useSecurity
© 2026 Vascend Technologies · VAT IT04911550616
ascend