Scores updated · 15 tests both models report · How we compare
Every test, side by side
All 15 tests both models report. The winning score is in its model's colour; marks a score checked independently.
Other results15 tests
- MBPPGLM-4.5-Base by 981.672.6+9
- MATHHunyuan Large by 8.86169.8+8.8
- HumanEvalGLM-4.5-Base by 6.878.271.4+6.8
- C-EvalHunyuan Large by 6.185.891.9+6.1
- DROPHunyuan Large by 682.988.9+6
- CMMLUHunyuan Large by 3.786.590.2+3.7
- PIQAHunyuan Large by 3.684.788.3+3.6
- MMLU-ProGLM-4.5-Base by 3.563.760.2+3.5
- WinoGrandeHunyuan Large by 3.585.288.7+3.5
- HellaSwagGLM-4.5-Base by 3.490.286.8+3.4
- GSM8KHunyuan Large by 2.790.192.8+2.7
- CMathHunyuan Large by 289.391.3+2
- ARC-ChallengeGLM-4.5-Base by 1.396.395+1.3
- MMLUtie87.788.4tie
- BBHtie86.286.3tie
Questions people ask
How do you compare the two?
We use the 15 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.