DeepSeek-R1 vs Z-1

Side-by-side benchmark comparison across knowledge, coding, math, and reasoning.

Quick Verdict

Z-1 wins overall with a score of 43 vs 35 (8 point difference).Z-1 wins 4 out of 4 categories.

Knowledge

Z-1

DeepSeek-R1

41.8

Z-1

49.8

44
MMLU
52
43
GPQA
51
41
SuperGPQA
49
39
OpenBookQA
47

Coding

Z-1

DeepSeek-R1

36

Z-1

44

36
HumanEval
44

Mathematics

Z-1

DeepSeek-R1

43

Z-1

51

44
AIME 2023
52
46
AIME 2024
54
45
AIME 2025
53
40
HMMT Feb 2023
48
42
HMMT Feb 2024
50
41
HMMT Feb 2025
49
43
BRUMO 2025
51

Reasoning

Z-1

DeepSeek-R1

41

Z-1

49

42
SimpleQA
50
40
MuSR
48

Frequently Asked Questions

Which is better, DeepSeek-R1 or Z-1?

Z-1 scores higher overall with 43 vs 35, a difference of 8 points across all benchmarks.

Which is better for knowledge tasks, DeepSeek-R1 or Z-1?

Z-1 leads in knowledge tasks with an average score of 49.8 vs 41.8.

Which is better for coding, DeepSeek-R1 or Z-1?

Z-1 leads in coding with an average score of 44 vs 36.

Which is better for math, DeepSeek-R1 or Z-1?

Z-1 leads in math with an average score of 51 vs 43.

Which is better for reasoning, DeepSeek-R1 or Z-1?

Z-1 leads in reasoning with an average score of 49 vs 41.