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

Hermes 4 - Llama-3.1 405B (Non-reasoning)

  • Nous Research
  • Release · August 27, 2025
  • Open weights
  • Non-reasoning

Intelligence

Intelligence Index

#205 of 266
  1. 7.57.5Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)
  2. 7.57.5ERNIE 4.5 300B A47B
  3. 7.57.5NVIDIA Nemotron Nano 12B v2 VL (Reasoning)
  4. 7.57.5Gemma 4 E4B (Non-reasoning)
  5. 7.57.5Hermes 4 - Llama-3.1 405B (Reasoning)
  6. 7.47.4Hermes 4 - Llama-3.1 405B (Non-reasoning)
  7. 7.47.4NVIDIA Nemotron Nano 9B V2 (Reasoning)
  8. 7.37.3K2-V2 (Low)
  9. 7.37.3Llama 3.1 Instruct 405B
  10. 7.37.3Kimi Linear 48B A3B Instruct
Data from Artificial Analysis

Evaluations

  • AA-Omniscience Accuracy26.1%#87
  • Humanity's Last Exam4.2%#240
  • AA-LCR22%#189
  • CritPt0%#143
  • GPQA Diamond53.6%#162
  • IFBench34.8%#108
  • τ²-Bench Telecom26.6%#87
  • Terminal-Bench Hard9.9%#60
Hermes 4 - Llama-3.1 405B (Non-reasoning)Median
Data from Artificial Analysis

Speed and price

Speed

tokens per second · #153 of 162
  1. 4848Granite 4.2 30B
  2. 4646Phi-4 Mini Instruct
  3. 4545Gemma 4 E4B (Reasoning)
  4. 4545Qwen3.8 27B (Xhigh)
  5. 4545Gemma 4 E4B (Non-reasoning)
  6. 4343Hermes 4 - Llama-3.1 405B (Non-reasoning)
  7. 4343Hermes 4 - Llama-3.1 405B (Reasoning)
  8. 4141Qwen3.8 2.4T A95B
  9. 4040Qwen3.8 Max (0902)
  10. 3939Phi-4
Data from Artificial Analysis

Latency

seconds to first token · #90 of 162
  1. 2.22.2K2 Horizon 375B A23B
  2. 2.22.2GPT-5.6 Terra (High)
  3. 2.22.2Gemma 4 12B (Reasoning)
  4. 2.32.3Gemma 4 12B (Non-reasoning)
  5. 2.32.3Qwen3.5 122B A10B (Reasoning)
  6. 2.32.3Hermes 4 - Llama-3.1 405B (Non-reasoning)
  7. 2.32.3Qwen3.7 Plus
  8. 2.32.3Qwen3.5 122B A10B (Non-reasoning)
  9. 2.32.3Hermes 4 - Llama-3.1 405B (Reasoning)
  10. 2.32.3GPT-6 Astra (Low)
Data from Artificial Analysis

Price

$ per 1M tokens (3:1) · #113 of 169
  1. $1.51.5Gemini 3.8 Flash (High)
  2. $1.51.5Gemini 3.8 Flash (Medium)
  3. $1.51.5Gemini 3.8 Flash (Low)
  4. $1.51.5Qwen3.5 Omni Plus
  5. $1.51.5Hermes 4 - Llama-3.1 405B (Reasoning)
  6. $1.51.5Hermes 4 - Llama-3.1 405B (Non-reasoning)
  7. $1.711.71Kimi K2.7 Code
  8. $1.761.76Inkling (Xhigh)
  9. $1.981.98DeepSeek V4 Pro 0813 (Max)
  10. $1.981.98DeepSeek V4 Pro 0813 (Non-reasoning)
Data from Artificial Analysis

Nearby models

  • 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
  • Gemma 4 E4B (Non-reasoning)Google7.5
  • Hermes 4 - Llama-3.1 405B (Reasoning)Nous Research7.5
  • NVIDIA Nemotron Nano 9B V2 (Reasoning)NVIDIA7.4
  • K2-V2 (Low)Institute of Foundation Models7.3
  • Llama 3.1 Instruct 405BMeta7.3
Data from Artificial Analysis

Same lab

  • Hermes 4 - Llama-3.1 70B (Reasoning)Nous Research7.9
  • Hermes 4 - Llama-3.1 70B (Non-reasoning)Nous Research6.7
  • DeepHermes 3 - Mistral 24B Preview (Non-reasoning)Nous Research6.1
  • DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning)Nous Research5.1
Data from Artificial Analysis
HorizonVascend IDEOlympusTalosCoursesCommunityBenchmark
DiscordGitHubXLet’s talkLegalPrivacyCookiesData useSecurity
© 2026 Vascend Technologies · VAT IT04911550616
ascend