Hy3-preview-Base is the stronger all-rounder.
Scores updated · 20 tests both models report · How we compare
Where each one wins
Tests won in each of the one area where both have results. Each piece is one test, so a longer bar means more evidence; grey means the two scored within a point of each other.
Coding rests on a single test.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where Hy3-preview-Base pulls ahead
- Recent programming contest problemsLiveCodeBench v6+7.5points ahead
Where GLM-4.5-Base pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 20 tests both models report. The winning score is in its model's colour; marks a score checked independently.
Other results19 tests, not counted
Tests outside the eight areas. They are not counted above: several are summary scores built from other tests, or the same test under another name.
- MATHHy3-preview-Base by 15.36176.3+15.3
- GSM8KHy3-preview-Base by 5.390.195.4+5.3
- C-EvalHy3-preview-Base by 485.889.8+4
- CMMLUHy3-preview-Base by 3.186.589.6+3.1
- SimpleQAGLM-4.5-Base by 2.829.326.5+2.8
- CRUXEval-I (input prediction)Hy3-preview-Base by 2.768.571.2+2.7
- DROPHy3-preview-Base by 2.682.985.5+2.6
- IncludeHy3-preview-Base by 2.376.378.6+2.3
- MMLU-ProHy3-preview-Base by 2.163.765.8+2.1
- SuperGPQAHy3-preview-Base by 249.651.6+2
- CMathHy3-preview-Base by 1.989.391.2+1.9
- Chinese SimpleQA (C-SimpleQA)Hy3-preview-Base by 1.268.569.7+1.2
- MMMLUtie79.380.2tie
- CRUXEval-O (output prediction)tie67.868.4tie
- MBPP+ (EvalPlus-augmented)tie7878.7tie
- ARC-Challengetie96.396tie
- MMLUtie87.787.4tie
- MMLU-Reduxtie86.686.9tie
- PIQAtie84.784.4tie
Questions people ask
Which is better, GLM-4.5-Base or Hy3-preview-Base?
Hy3-preview-Base wins the one area where both have results: coding. GLM-4.5-Base wins none.
Which is better for coding?
Hy3-preview-Base. It wins the one coding test both models report.
How do you compare the two?
We use the 20 benchmark tests both models have published scores on. The verdict counts the 1 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 19 are listed but not counted, because several are summary scores or repeat a test. Each score is the one shown on the model's own page.