Mercury 2 vs Gemma 3 27B

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

Mercury 2 is clearly ahead on the aggregate, 65 to 38. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Mercury 2's sharpest advantage is in reasoning, where it averages 80.1 against 45.6. The single biggest benchmark swing on the page is MuSR, 82 to 41.

Mercury 2 is the reasoning model in the pair, while Gemma 3 27B 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. Mercury 2 gives you the larger context window at 128K, compared with 32K for Gemma 3 27B.

Quick Verdict

Pick Mercury 2 if you want the stronger benchmark profile. Gemma 3 27B only becomes the better choice if you would rather avoid the extra latency and token burn of a reasoning model.

Agentic

Mercury 2

Mercury 2

63.7

Gemma 3 27B

34.4

63
Terminal-Bench 2.0
29
67
BrowseComp
42
62
OSWorld-Verified
35

Coding

Mercury 2

Mercury 2

41.1

Gemma 3 27B

16

75
HumanEval
37
46
SWE-bench Verified
16
38
LiveCodeBench
15
43
SWE-bench Pro
17

Multimodal & Grounded

Mercury 2

Mercury 2

68.3

Gemma 3 27B

41.7

66
MMMU-Pro
39
71
OfficeQA Pro
45

Reasoning

Mercury 2

Mercury 2

80.1

Gemma 3 27B

45.6

82
SimpleQA
43
82
MuSR
41
87
BBH
62
77
LongBench v2
47
76
MRCRv2
44

Knowledge

Mercury 2

Mercury 2

57.2

Gemma 3 27B

34.6

78
MMLU
45
78
GPQA
44
76
SuperGPQA
42
74
OpenBookQA
40
72
MMLU-Pro
50
9
HLE
3
69
FrontierScience
42

Instruction Following

Mercury 2

Mercury 2

84

Gemma 3 27B

67

84
IFEval
67

Multilingual

Mercury 2

Mercury 2

79.7

Gemma 3 27B

61.4

81
MGSM
64
79
MMLU-ProX
60

Mathematics

Mercury 2

Mercury 2

80.9

Gemma 3 27B

49.4

81
AIME 2023
45
83
AIME 2024
47
82
AIME 2025
46
77
HMMT Feb 2023
41
79
HMMT Feb 2024
43
78
HMMT Feb 2025
42
80
BRUMO 2025
44
82
MATH-500
56

Frequently Asked Questions

Which is better, Mercury 2 or Gemma 3 27B?

Mercury 2 is ahead overall, 65 to 38. The biggest single separator in this matchup is MuSR, where the scores are 82 and 41.

Which is better for knowledge tasks, Mercury 2 or Gemma 3 27B?

Mercury 2 has the edge for knowledge tasks in this comparison, averaging 57.2 versus 34.6. Inside this category, GPQA is the benchmark that creates the most daylight between them.

Which is better for coding, Mercury 2 or Gemma 3 27B?

Mercury 2 has the edge for coding in this comparison, averaging 41.1 versus 16. Inside this category, HumanEval is the benchmark that creates the most daylight between them.

Which is better for math, Mercury 2 or Gemma 3 27B?

Mercury 2 has the edge for math in this comparison, averaging 80.9 versus 49.4. Inside this category, AIME 2023 is the benchmark that creates the most daylight between them.

Which is better for reasoning, Mercury 2 or Gemma 3 27B?

Mercury 2 has the edge for reasoning in this comparison, averaging 80.1 versus 45.6. Inside this category, MuSR is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, Mercury 2 or Gemma 3 27B?

Mercury 2 has the edge for agentic tasks in this comparison, averaging 63.7 versus 34.4. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.

Which is better for multimodal and grounded tasks, Mercury 2 or Gemma 3 27B?

Mercury 2 has the edge for multimodal and grounded tasks in this comparison, averaging 68.3 versus 41.7. Inside this category, MMMU-Pro is the benchmark that creates the most daylight between them.

Which is better for instruction following, Mercury 2 or Gemma 3 27B?

Mercury 2 has the edge for instruction following in this comparison, averaging 84 versus 67. Inside this category, IFEval is the benchmark that creates the most daylight between them.

Which is better for multilingual tasks, Mercury 2 or Gemma 3 27B?

Mercury 2 has the edge for multilingual tasks in this comparison, averaging 79.7 versus 61.4. Inside this category, MMLU-ProX 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.