Mercury 2 vs DeepSeek V3.2

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

Mercury 2 finishes one point ahead overall, 65 to 64. That is enough to call, but not enough to treat as a blowout. This matchup comes down to a few meaningful edges rather than one model dominating the board.

Mercury 2's sharpest advantage is in agentic, where it averages 63.7 against 58.8. The single biggest benchmark swing on the page is LongBench v2, 77 to 69. DeepSeek V3.2 does hit back in knowledge, so the answer changes if that is the part of the workload you care about most.

Mercury 2 is the reasoning model in the pair, while DeepSeek V3.2 is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use.

Quick Verdict

Pick Mercury 2 if you want the stronger benchmark profile. DeepSeek V3.2 only becomes the better choice if knowledge is the priority or you would rather avoid the extra latency and token burn of a reasoning model.

Agentic

Mercury 2

Mercury 2

63.7

DeepSeek V3.2

58.8

63
Terminal-Bench 2.0
60
67
BrowseComp
62
62
OSWorld-Verified
55

Coding

DeepSeek V3.2

Mercury 2

41.1

DeepSeek V3.2

43.2

75
HumanEval
76
46
SWE-bench Verified
45
38
LiveCodeBench
39
43
SWE-bench Pro
47

Multimodal & Grounded

Mercury 2

Mercury 2

68.3

DeepSeek V3.2

66

66
MMMU-Pro
61
71
OfficeQA Pro
72

Reasoning

Mercury 2

Mercury 2

80.1

DeepSeek V3.2

75.3

82
SimpleQA
81
82
MuSR
79
87
BBH
81
77
LongBench v2
69
76
MRCRv2
70

Knowledge

DeepSeek V3.2

Mercury 2

57.2

DeepSeek V3.2

60

78
MMLU
84
78
GPQA
83
76
SuperGPQA
81
74
OpenBookQA
79
72
MMLU-Pro
73
9
HLE
11
69
FrontierScience
72

Instruction Following

DeepSeek V3.2

Mercury 2

84

DeepSeek V3.2

85

84
IFEval
85

Multilingual

DeepSeek V3.2

Mercury 2

79.7

DeepSeek V3.2

82.1

81
MGSM
84
79
MMLU-ProX
81

Mathematics

DeepSeek V3.2

Mercury 2

80.9

DeepSeek V3.2

82.1

81
AIME 2023
84
83
AIME 2024
86
82
AIME 2025
85
77
HMMT Feb 2023
80
79
HMMT Feb 2024
82
78
HMMT Feb 2025
81
80
BRUMO 2025
83
82
MATH-500
81

Frequently Asked Questions

Which is better, Mercury 2 or DeepSeek V3.2?

Mercury 2 is ahead overall, 65 to 64. The biggest single separator in this matchup is LongBench v2, where the scores are 77 and 69.

Which is better for knowledge tasks, Mercury 2 or DeepSeek V3.2?

DeepSeek V3.2 has the edge for knowledge tasks in this comparison, averaging 60 versus 57.2. Inside this category, MMLU is the benchmark that creates the most daylight between them.

Which is better for coding, Mercury 2 or DeepSeek V3.2?

DeepSeek V3.2 has the edge for coding in this comparison, averaging 43.2 versus 41.1. Inside this category, SWE-bench Pro is the benchmark that creates the most daylight between them.

Which is better for math, Mercury 2 or DeepSeek V3.2?

DeepSeek V3.2 has the edge for math in this comparison, averaging 82.1 versus 80.9. Inside this category, AIME 2023 is the benchmark that creates the most daylight between them.

Which is better for reasoning, Mercury 2 or DeepSeek V3.2?

Mercury 2 has the edge for reasoning in this comparison, averaging 80.1 versus 75.3. Inside this category, LongBench v2 is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, Mercury 2 or DeepSeek V3.2?

Mercury 2 has the edge for agentic tasks in this comparison, averaging 63.7 versus 58.8. Inside this category, OSWorld-Verified is the benchmark that creates the most daylight between them.

Which is better for multimodal and grounded tasks, Mercury 2 or DeepSeek V3.2?

Mercury 2 has the edge for multimodal and grounded tasks in this comparison, averaging 68.3 versus 66. Inside this category, MMMU-Pro is the benchmark that creates the most daylight between them.

Which is better for instruction following, Mercury 2 or DeepSeek V3.2?

DeepSeek V3.2 has the edge for instruction following in this comparison, averaging 85 versus 84. Inside this category, IFEval is the benchmark that creates the most daylight between them.

Which is better for multilingual tasks, Mercury 2 or DeepSeek V3.2?

DeepSeek V3.2 has the edge for multilingual tasks in this comparison, averaging 82.1 versus 79.7. Inside this category, MGSM is the benchmark that creates the most daylight between them.

Last updated: March 12, 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.