VECTOR WIREAI INTELLIGENCE
⌘K
PKT
Refresh Models —Deals —Regulatory —Sources —

Questions this page answers

Which is better, DeepSeek-V2 or ERNIE 4.5?
Across 13 shared benchmarks, DeepSeek-V2 scores higher on 12 and ERNIE 4.5 on 1. The widest gap is MMLU-Pro, where DeepSeek-V2 scores 58.5 against 16.

DeepSeek-V2 vs ERNIE 4.5

Across 13 shared benchmarks, DeepSeek-V2 scores higher on 12 and ERNIE 4.5 on 1. The widest gap is MMLU-Pro, where DeepSeek-V2 scores 58.5 against 16.

DeepSeekvsBaidu13 shared benchmarks12–1 head-to-head
BenchmarkDeepSeek-V2ERNIE 4.5
arc_challenge92.440.6
bbh78.930.4
C-Eval81.740.7
CLUEWSC89.948.6
cmmlu8439.8
DROP80.128.6
GPQA Diamond35.374
GSM8K79.225.2
hellaswag87.833
mmlu_redux77.943.2
MMLU-Pro58.516
PIQA83.955.2
winogrande86.351.3

Best tracked score per model per benchmark (default configuration; source-attributed). ↓ marks lower-is-better metrics. Open either model for its full surface, provenance and pricing.