DeepSeek-V3 is the stronger all-rounder.
Scores updated · 26 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.
What it costs
Prices per million tokens, roughly 750,000 words. The bars show the cost of a million tokens read plus a million written.
The biggest differences
The tests each model wins by the widest margin, up to three each. Scores are out of 100.
Where DeepSeek-V3 pulls ahead
- Graduate-level biology, physics and chemistry questionsGPQA Diamond+30.6points ahead
- Recent programming contest problemsLiveCodeBench v6+19.5points ahead
Where GLM-4.5-Base pulls ahead
No clear win on a test scored out of 100.
Every test, side by side
All 26 tests both models report. The winning score is in its model's colour; marks a score checked independently.
Other results24 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.
- OpenBookQADeepSeek-V3 by 45.895.449.6+45.8
- MATHDeepSeek-V3 by 29.290.261+29.2
- HumanEvalGLM-4.5-Base by 1365.278.2+13
- MMLU-ProDeepSeek-V3 by 12.275.963.7+12.2
- DROPDeepSeek-V3 by 8.791.682.9+8.7
- MBPPGLM-4.5-Base by 6.275.481.6+6.2
- SimpleQAGLM-4.5-Base by 4.424.929.3+4.4
- SuperGPQADeepSeek-V3 by 4.153.749.6+4.1
- GSM8KDeepSeek-V3 by 3.99490.1+3.9
- MMLU-ReduxDeepSeek-V3 by 2.589.186.6+2.5
- CMMLUDeepSeek-V3 by 2.388.886.5+2.3
- CRUXEval-O (output prediction)DeepSeek-V3 by 269.867.8+2
- MGSMGLM-4.5-Base by 1.579.881.3+1.5
- BBHDeepSeek-V3 by 1.387.586.2+1.3
- HellaSwagGLM-4.5-Base by 1.388.990.2+1.3
- CRUXEval-I (input prediction)GLM-4.5-Base by 1.267.368.5+1.2
- ARC-ChallengeGLM-4.5-Base by 195.396.3+1
- MMLUtie88.587.7tie
- C-Evaltie86.585.8tie
- MBPP+ (EvalPlus-augmented)tie78.878tie
- Chinese SimpleQA (C-SimpleQA)tie6868.5tie
- WinoGrandetie84.985.2tie
- MMMLUtie79.479.3tie
- PIQAtie84.784.7tie
Questions people ask
Which is better, DeepSeek-V3 or GLM-4.5-Base?
DeepSeek-V3 wins all two areas where both have results: coding and reasoning. GLM-4.5-Base wins none.
Which is better for coding?
DeepSeek-V3. It wins the one coding test both models report.
How do you compare the two?
We use the 26 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 24 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.