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

Hermes 4 - Llama-3.1 405B (Reasoning)

  • Nous Research
  • Open weights
  • Reasoning

Intelligence

Intelligence Index

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

Evaluations

  • AA-Omniscience Accuracy30.1%#78
  • Humanity's Last Exam10.9%#144
  • AA-LCR22.3%#188
  • CritPt0.3%#117
  • GPQA Diamond72.7%#109
  • IFBench32.7%#117
  • τ²-Bench Telecom22.2%#98
  • Terminal-Bench Hard11.4%#53
Hermes 4 - Llama-3.1 405B (Reasoning)Median
Data from Artificial Analysis

Speed and price

Speed

tokens per second · #154 of 162
  1. 4646Phi-4 Mini Instruct
  2. 4545Gemma 4 E4B (Reasoning)
  3. 4545Qwen3.8 27B (Xhigh)
  4. 4545Gemma 4 E4B (Non-reasoning)
  5. 4343Hermes 4 - Llama-3.1 405B (Non-reasoning)
  6. 4343Hermes 4 - Llama-3.1 405B (Reasoning)
  7. 4141Qwen3.8 2.4T A95B
  8. 4040Qwen3.8 Max (0902)
  9. 3939Phi-4
  10. 3535Gemma 4 31B (Reasoning)
Data from Artificial Analysis

Latency

seconds to first token · #93 of 162
  1. 2.32.3Gemma 4 12B (Non-reasoning)
  2. 2.32.3Qwen3.5 122B A10B (Reasoning)
  3. 2.32.3Hermes 4 - Llama-3.1 405B (Non-reasoning)
  4. 2.32.3Qwen3.7 Plus
  5. 2.32.3Qwen3.5 122B A10B (Non-reasoning)
  6. 2.32.3Hermes 4 - Llama-3.1 405B (Reasoning)
  7. 2.32.3GPT-6 Astra (Low)
  8. 2.42.4Mistral Medium 3.5
  9. 2.42.4GLM-5.3 (Max)
  10. 2.52.5GPT-6 Luna (Low)
Data from Artificial Analysis

Price

$ per 1M tokens (3:1) · #112 of 169
  1. $1.431.43Step 5 Preview
  2. $1.51.5Gemini 3.8 Flash (High)
  3. $1.51.5Gemini 3.8 Flash (Medium)
  4. $1.51.5Gemini 3.8 Flash (Low)
  5. $1.51.5Qwen3.5 Omni Plus
  6. $1.51.5Hermes 4 - Llama-3.1 405B (Reasoning)
  7. $1.51.5Hermes 4 - Llama-3.1 405B (Non-reasoning)
  8. $1.711.71Kimi K2.7 Code
  9. $1.761.76Inkling (Xhigh)
  10. $1.981.98DeepSeek V4 Pro 0813 (Max)
Data from Artificial Analysis

Nearby models

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