GLM-4.5-Base is the stronger all-rounder.
Scores updated · 33 tests both models report · How we compare
Where each one wins
Tests won in each of the two areas 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 and reasoning rest on a single test each.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where GLM-4.5-Base pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+3.1points ahead
- Recent programming contest problemsLiveCodeBench v6+2.5points ahead
Where DeepSeek-V3.2-Exp-Base pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 33 tests both models report. The winning score is in its model's colour; marks a score checked independently.
Other results31 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.
- RULER 128KDeepSeek-V3.2-Exp-Base by 91.991.90+91.9
- RULER 64KDeepSeek-V3.2-Exp-Base by 77.293.316.1+77.2
- MBPP-SanitizedGLM-4.5-Base by 1858.776.7+18
- HumanEvalGLM-4.5-Base by 16.361.978.2+16.3
- MBPP+ (EvalPlus-augmented)GLM-4.5-Base by 8.369.878+8.3
- CRUXEval-O (output prediction)DeepSeek-V3.2-Exp-Base by 7.174.967.8+7.1
- MBPPGLM-4.5-Base by 675.681.6+6
- SuperGPQAGLM-4.5-Base by 643.649.6+6
- GSM8KGLM-4.5-Base by 5.784.490.1+5.7
- C-EvalDeepSeek-V3.2-Exp-Base by 5.29185.8+5.2
- CRUXEval-I (input prediction)GLM-4.5-Base by 4.663.968.5+4.6
- GPQA (unspecified)DeepSeek-V3.2-Exp-Base by 3.837.333.5+3.8
- MMLU-ReduxDeepSeek-V3.2-Exp-Base by 3.890.486.6+3.8
- DROPDeepSeek-V3.2-Exp-Base by 3.786.682.9+3.7
- BBHDeepSeek-V3.2-Exp-Base by 2.588.786.2+2.5
- CMMLUDeepSeek-V3.2-Exp-Base by 2.488.986.5+2.4
- SimpleQAGLM-4.5-Base by 2.32729.3+2.3
- WinoGrandeGLM-4.5-Base by 1.883.485.2+1.8
- OpenBookQAGLM-4.5-Base by 1.448.249.6+1.4
- ARC-ChallengeGLM-4.5-Base by 1.195.296.3+1.1
- MGSMDeepSeek-V3.2-Exp-Base by 182.381.3+1
- RACEDeepSeek-V3.2-Exp-Base by 193.292.2+1
- Includetie77.276.3tie
- MATHtie60.161tie
- HellaSwagtie89.490.2tie
- Chinese SimpleQA (C-SimpleQA)tie6868.5tie
- MMLU-Protie63.363.7tie
- PIQAtie85.184.7tie
- Global-MMLU-Litetie85.685.8tie
- MMLUtie87.887.7tie
- AGIEval-Entie70.170.1tie
Questions people ask
Which is better, DeepSeek-V3.2-Exp-Base or GLM-4.5-Base?
GLM-4.5-Base wins all two areas where both have results: coding and reasoning. DeepSeek-V3.2-Exp-Base wins none.
Which is better for coding?
GLM-4.5-Base. It wins the one coding test both models report.
How do you compare the two?
We use the 33 benchmark tests both models have published scores on. The verdict counts the 2 tests in the eight capability areas, and a gap under one point (ten on rating-style scales) counts as a tie. The other 31 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.