Skip to content
VECTOR WIREAI INTELLIGENCE
UTC

ERNIE 5.5 Flash Base vs MiMo V2.5 Base

Baidu · released

Xiaomi · released

Scores updated · 24 tests both models report · How we compare

Every test, side by side

All 24 tests both models report. The winning score is in its model's colour; marks a score checked independently.

Other results24 tests
  • RepoQA (Pass@1)ERNIE 5.5 Flash Base by 35.291.756.5+35.2
  • MathBench-CN (LLM-Judge)ERNIE 5.5 Flash Base by 15.280.865.6+15.2
  • SimpleQA (LLM-Judge)ERNIE 5.5 Flash Base by 13.334.120.8+13.3
  • HumanEval+ERNIE 5.5 Flash Base by 1182.371.3+11
  • MBPP+ERNIE 5.5 Flash Base by 10.681.570.9+10.6
  • BBH (EM, direct)ERNIE 5.5 Flash Base by 9.177.168+9.1
  • GPQA (EM)ERNIE 5.5 Flash Base by 8.860.251.4+8.8
  • MMMLU-lite (EM)ERNIE 5.5 Flash Base by 8.88172.2+8.8
  • LiveCodeBenchERNIE 5.5 Flash Base by 7.740.132.4+7.7
  • HotpotQA (LLM-Judge)ERNIE 5.5 Flash Base by 7.257.350.1+7.2
  • MultiLoKo (LLM-Judge)ERNIE 5.5 Flash Base by 743.336.3+7
  • PopQA (LLM-Judge)ERNIE 5.5 Flash Base by 6.552.245.7+6.5
  • INCLUDE-lite (EM)ERNIE 5.5 Flash Base by 579.574.5+5
  • ChineseSimpleQA (LLM-Judge)ERNIE 5.5 Flash Base by 4.27368.8+4.2
  • LongBench-V2 (EM)ERNIE 5.5 Flash Base by 4.148.744.6+4.1
  • MGSM (EM)ERNIE 5.5 Flash Base by 3.28783.8+3.2
  • WinoGrande (EM)ERNIE 5.5 Flash Base by 2.687.885.2+2.6
  • HELMET-RAG (SubEM)ERNIE 5.5 Flash Base by 2.571.569+2.5
  • PIQA (EM)ERNIE 5.5 Flash Base by 2.49693.6+2.4
  • CMMLU (EM)ERNIE 5.5 Flash Base by 2.39087.7+2.3
  • RepoBench (EM)ERNIE 5.5 Flash Base by 1.450.348.9+1.4
  • BBH (EM, CoT) (Pass@1 with chain-of-thought)tie89.289.8tie
  • FullStackBenchtie54.654.1tie
  • InfiniteBench (Avg)tie46.546.7tie

Questions people ask

How do you compare the two?

We use the 24 benchmark tests both models have published scores on. None of them is in the eight capability areas we count, so this page lists them without a verdict. Each score is the one shown on the model's own page.