Mercury 2 vs Nova Pro

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 46.3. The single biggest benchmark swing on the page is MuSR, 82 to 37.

Mercury 2 is the reasoning model in the pair, while Nova Pro 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. Nova Pro 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

Nova Pro

33.3

63
Terminal-Bench 2.0
31
67
BrowseComp
39
62
OSWorld-Verified
32

Coding

Mercury 2

Mercury 2

41.1

Nova Pro

17.2

75
HumanEval
33
46
SWE-bench Verified
19
38
LiveCodeBench
14
43
SWE-bench Pro
20

Multimodal & Grounded

Mercury 2

Mercury 2

68.3

Nova Pro

41.1

66
MMMU-Pro
37
71
OfficeQA Pro
46

Reasoning

Mercury 2

Mercury 2

80.1

Nova Pro

46.3

82
SimpleQA
39
82
MuSR
37
87
BBH
63
77
LongBench v2
51
76
MRCRv2
51

Knowledge

Mercury 2

Mercury 2

57.2

Nova Pro

34.2

78
MMLU
41
78
GPQA
40
76
SuperGPQA
38
74
OpenBookQA
36
72
MMLU-Pro
53
9
HLE
4
69
FrontierScience
41

Instruction Following

Mercury 2

Mercury 2

84

Nova Pro

66

84
IFEval
66

Multilingual

Mercury 2

Mercury 2

79.7

Nova Pro

60.4

81
MGSM
61
79
MMLU-ProX
60

Mathematics

Mercury 2

Mercury 2

80.9

Nova Pro

48.6

81
AIME 2023
41
83
AIME 2024
43
82
AIME 2025
42
77
HMMT Feb 2023
37
79
HMMT Feb 2024
39
78
HMMT Feb 2025
38
80
BRUMO 2025
40
82
MATH-500
59

Frequently Asked Questions

Which is better, Mercury 2 or Nova Pro?

Mercury 2 is ahead overall, 65 to 38. The biggest single separator in this matchup is MuSR, where the scores are 82 and 37.

Which is better for knowledge tasks, Mercury 2 or Nova Pro?

Mercury 2 has the edge for knowledge tasks in this comparison, averaging 57.2 versus 34.2. Inside this category, GPQA is the benchmark that creates the most daylight between them.

Which is better for coding, Mercury 2 or Nova Pro?

Mercury 2 has the edge for coding in this comparison, averaging 41.1 versus 17.2. Inside this category, HumanEval is the benchmark that creates the most daylight between them.

Which is better for math, Mercury 2 or Nova Pro?

Mercury 2 has the edge for math in this comparison, averaging 80.9 versus 48.6. Inside this category, AIME 2023 is the benchmark that creates the most daylight between them.

Which is better for reasoning, Mercury 2 or Nova Pro?

Mercury 2 has the edge for reasoning in this comparison, averaging 80.1 versus 46.3. Inside this category, MuSR is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, Mercury 2 or Nova Pro?

Mercury 2 has the edge for agentic tasks in this comparison, averaging 63.7 versus 33.3. 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 Nova Pro?

Mercury 2 has the edge for multimodal and grounded tasks in this comparison, averaging 68.3 versus 41.1. Inside this category, MMMU-Pro is the benchmark that creates the most daylight between them.

Which is better for instruction following, Mercury 2 or Nova Pro?

Mercury 2 has the edge for instruction following in this comparison, averaging 84 versus 66. Inside this category, IFEval is the benchmark that creates the most daylight between them.

Which is better for multilingual tasks, Mercury 2 or Nova Pro?

Mercury 2 has the edge for multilingual tasks in this comparison, averaging 79.7 versus 60.4. 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.