DeepSeek V3 vs Qwen2.5-72B

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

Qwen2.5-72B is clearly ahead on the aggregate, 36 to 25. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Qwen2.5-72B's sharpest advantage is in reasoning, where it averages 78.9 against 24.9. The single biggest benchmark swing on the page is SimpleQA, 24.9% to 80%. DeepSeek V3 does hit back in mathematics, so the answer changes if that is the part of the workload you care about most.

Quick Verdict

Pick Qwen2.5-72B if you want the stronger benchmark profile. DeepSeek V3 only becomes the better choice if mathematics is the priority.

Agentic

Coming soon

Benchmark data for this category is coming soon.

Coding

DeepSeek V3

DeepSeek V3

42

Qwen2.5-72B

35.7

42%
SWE-bench Verified
Coming soon
Coming soon
HumanEval
86%
Coming soon
LiveCodeBench
35.7%

Multimodal & Grounded

Coming soon

Benchmark data for this category is coming soon.

Reasoning

Qwen2.5-72B

DeepSeek V3

24.9

Qwen2.5-72B

78.9

24.9%
SimpleQA
80%
Coming soon
MuSR
78%

Knowledge

DeepSeek V3

DeepSeek V3

69.6

Qwen2.5-72B

62.7

59.1%
GPQA
42.4%
88.5%
MMLU
82.3%
75.9%
MMLU-Pro
64.4%
Coming soon
SuperGPQA
80%
Coming soon
OpenBookQA
78%

Instruction Following

Coming soon

Comparable scores for this category are coming soon. One or both models do not have sourced results here yet.

Coming soon
IFEval
77.6%

Multilingual

Coming soon

Benchmark data for this category is coming soon.

Mathematics

DeepSeek V3

DeepSeek V3

90.2

Qwen2.5-72B

83

39.2%
AIME 2024
86%
90.2%
MATH-500
Coming soon
Coming soon
AIME 2023
84%
Coming soon
AIME 2025
85%
Coming soon
HMMT Feb 2023
80%
Coming soon
HMMT Feb 2024
82%
Coming soon
HMMT Feb 2025
81%
Coming soon
BRUMO 2025
83%

Frequently Asked Questions

Which is better, DeepSeek V3 or Qwen2.5-72B?

Qwen2.5-72B is ahead overall, 36 to 25. The biggest single separator in this matchup is SimpleQA, where the scores are 24.9% and 80%.

Which is better for knowledge tasks, DeepSeek V3 or Qwen2.5-72B?

DeepSeek V3 has the edge for knowledge tasks in this comparison, averaging 69.6 versus 62.7. Inside this category, GPQA is the benchmark that creates the most daylight between them.

Which is better for coding, DeepSeek V3 or Qwen2.5-72B?

DeepSeek V3 has the edge for coding in this comparison, averaging 42 versus 35.7. Qwen2.5-72B stays close enough that the answer can still flip depending on your workload.

Which is better for math, DeepSeek V3 or Qwen2.5-72B?

DeepSeek V3 has the edge for math in this comparison, averaging 90.2 versus 83. Inside this category, AIME 2024 is the benchmark that creates the most daylight between them.

Which is better for reasoning, DeepSeek V3 or Qwen2.5-72B?

Qwen2.5-72B has the edge for reasoning in this comparison, averaging 78.9 versus 24.9. Inside this category, SimpleQA is the benchmark that creates the most daylight between them.

Last updated: March 17, 2026

Weekly LLM Benchmark Digest

Get notified when new models drop, benchmark scores change, or the leaderboard shifts. One email per week.

Free. No spam. Unsubscribe anytime. We only store derived location metadata for consent routing.