The two are evenly matched.DeepSeek-V3.1-Base is better at reasoning; GLM-4.5-Base at coding.
Scores updated · 24 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 DeepSeek-V3.1-Base pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+16.1points ahead
Where GLM-4.5-Base pulls ahead
- Recent programming contest problemsLiveCodeBench v6+2.6points ahead
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 results22 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.
- GPQA (unspecified)DeepSeek-V3.1-Base by 9.643.133.5+9.6
- CRUXEval-O (output prediction)DeepSeek-V3.1-Base by 8.676.467.8+8.6
- SuperGPQAGLM-4.5-Base by 7.342.349.6+7.3
- MBPPGLM-4.5-Base by 774.681.6+7
- CRUXEval-I (input prediction)GLM-4.5-Base by 6.462.168.5+6.4
- MBPP+ (EvalPlus-augmented)GLM-4.5-Base by 5.972.278+5.9
- HumanEvalGLM-4.5-Base by 5.772.578.2+5.7
- MMLU-ProGLM-4.5-Base by 4.958.863.7+4.9
- C-EvalDeepSeek-V3.1-Base by 4.29085.8+4.2
- DROPDeepSeek-V3.1-Base by 3.486.382.9+3.4
- MMLU-ReduxDeepSeek-V3.1-Base by 3.49086.6+3.4
- SimpleQAGLM-4.5-Base by 326.329.3+3
- Chinese SimpleQA (C-SimpleQA)DeepSeek-V3.1-Base by 2.470.968.5+2.4
- CMMLUDeepSeek-V3.1-Base by 2.388.886.5+2.3
- BBHDeepSeek-V3.1-Base by 288.286.2+2
- MATHDeepSeek-V3.1-Base by 1.662.661+1.6
- GSM8KDeepSeek-V3.1-Base by 1.391.490.1+1.3
- HellaSwagGLM-4.5-Base by 189.290.2+1
- Includetie77.276.3tie
- ARC-Challengetie95.696.3tie
- WinoGrandetie85.985.2tie
- MMLUtie87.487.7tie
Questions people ask
Which is better, DeepSeek-V3.1-Base or GLM-4.5-Base?
DeepSeek-V3.1-Base and GLM-4.5-Base each win one of the two areas where both have results. DeepSeek-V3.1-Base wins reasoning; GLM-4.5-Base wins coding.
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 24 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 22 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.