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

ERNIE 4.5 300B A47B

  • Baidu
  • Release · June 30, 2025
  • Open weights
  • Non-reasoning

Intelligence

Intelligence Index

#201 of 266
  1. 7.87.8Qwen3 Omni 30B A3B (Reasoning)
  2. 7.87.8Gemma 4 E2B (Reasoning)
  3. 7.77.7Step3 VL 10B
  4. 7.77.7Llama 3.3 Instruct 70B
  5. 7.57.5Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)
  6. 7.57.5ERNIE 4.5 300B A47B
  7. 7.57.5NVIDIA Nemotron Nano 12B v2 VL (Reasoning)
  8. 7.57.5Gemma 4 E4B (Non-reasoning)
  9. 7.57.5Hermes 4 - Llama-3.1 405B (Reasoning)
  10. 7.47.4Hermes 4 - Llama-3.1 405B (Non-reasoning)
Data from Artificial Analysis

Evaluations

  • AA-Omniscience Accuracy19.1%#119
  • Humanity's Last Exam3.3%#260
  • CritPt0%#143
  • GPQA Diamond81.1%#68
  • IFBench39.1%#91
  • τ²-Bench Telecom0%#143
  • Terminal-Bench Hard6.1%#78
ERNIE 4.5 300B A47BMedian
Data from Artificial Analysis

Nearby models

  • Qwen3 Omni 30B A3B (Reasoning)Alibaba7.8
  • Gemma 4 E2B (Reasoning)Google7.8
  • Step3 VL 10BStepFun7.7
  • Llama 3.3 Instruct 70BMeta7.7
  • Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)NVIDIA7.5
  • 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
Data from Artificial Analysis

Same lab

  • ERNIE 5.0 Thinking PreviewBaidu14.3
Data from Artificial Analysis
HorizonVascend IDEOlympusTalosCoursesCommunityBenchmark
DiscordGitHubXLet’s talkLegalPrivacyCookiesData useSecurity
© 2026 Vascend Technologies · VAT IT04911550616
ascend