Grok 4 vs Mercury 2

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

Grok 4 finishes one point ahead overall, 66 to 65. 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.

Grok 4's sharpest advantage is in multimodal & grounded, where it averages 78.2 against 68.3. The single biggest benchmark swing on the page is MMMU-Pro, 80 to 66. Mercury 2 does hit back in agentic, 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 Grok 4 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 Grok 4 if you want the stronger benchmark profile. Mercury 2 only becomes the better choice if agentic is the priority or you want the stronger reasoning-first profile.

Agentic

Mercury 2

Grok 4

58.1

Mercury 2

63.7

57
Terminal-Bench 2.0
63
63
BrowseComp
67
56
OSWorld-Verified
62

Coding

Grok 4

Grok 4

43.1

Mercury 2

41.1

79
HumanEval
75
48
SWE-bench Verified
46
37
LiveCodeBench
38
48
SWE-bench Pro
43

Multimodal & Grounded

Grok 4

Grok 4

78.2

Mercury 2

68.3

80
MMMU-Pro
66
76
OfficeQA Pro
71

Reasoning

Mercury 2

Grok 4

77.4

Mercury 2

80.1

83
SimpleQA
82
81
MuSR
82
83
BBH
87
72
LongBench v2
77
71
MRCRv2
76

Knowledge

Grok 4

Grok 4

63.8

Mercury 2

57.2

87
MMLU
78
86
GPQA
78
84
SuperGPQA
76
82
OpenBookQA
74
77
MMLU-Pro
72
16
HLE
9
75
FrontierScience
69

Instruction Following

Mercury 2

Grok 4

82

Mercury 2

84

82
IFEval
84

Multilingual

Grok 4

Grok 4

80.8

Mercury 2

79.7

84
MGSM
81
79
MMLU-ProX
79

Mathematics

Grok 4

Grok 4

85.1

Mercury 2

80.9

87
AIME 2023
81
89
AIME 2024
83
88
AIME 2025
82
84
HMMT Feb 2023
77
86
HMMT Feb 2024
79
85
HMMT Feb 2025
78
87
BRUMO 2025
80
83
MATH-500
82

Frequently Asked Questions

Which is better, Grok 4 or Mercury 2?

Grok 4 is ahead overall, 66 to 65. The biggest single separator in this matchup is MMMU-Pro, where the scores are 80 and 66.

Which is better for knowledge tasks, Grok 4 or Mercury 2?

Grok 4 has the edge for knowledge tasks in this comparison, averaging 63.8 versus 57.2. Inside this category, MMLU is the benchmark that creates the most daylight between them.

Which is better for coding, Grok 4 or Mercury 2?

Grok 4 has the edge for coding in this comparison, averaging 43.1 versus 41.1. Inside this category, SWE-bench Pro is the benchmark that creates the most daylight between them.

Which is better for math, Grok 4 or Mercury 2?

Grok 4 has the edge for math in this comparison, averaging 85.1 versus 80.9. Inside this category, HMMT Feb 2023 is the benchmark that creates the most daylight between them.

Which is better for reasoning, Grok 4 or Mercury 2?

Mercury 2 has the edge for reasoning in this comparison, averaging 80.1 versus 77.4. Inside this category, LongBench v2 is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, Grok 4 or Mercury 2?

Mercury 2 has the edge for agentic tasks in this comparison, averaging 63.7 versus 58.1. 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, Grok 4 or Mercury 2?

Grok 4 has the edge for multimodal and grounded tasks in this comparison, averaging 78.2 versus 68.3. Inside this category, MMMU-Pro is the benchmark that creates the most daylight between them.

Which is better for instruction following, Grok 4 or Mercury 2?

Mercury 2 has the edge for instruction following in this comparison, averaging 84 versus 82. Inside this category, IFEval is the benchmark that creates the most daylight between them.

Which is better for multilingual tasks, Grok 4 or Mercury 2?

Grok 4 has the edge for multilingual tasks in this comparison, averaging 80.8 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.