GLM-4.7 vs Mercury 2

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

GLM-4.7 has the cleaner overall profile here, landing at 67 versus 65. It is a real lead, but still close enough that category-level strengths matter more than the headline number.

GLM-4.7's sharpest advantage is in coding, where it averages 46.6 against 41.1. The single biggest benchmark swing on the page is SWE-bench Pro, 51 to 43. Mercury 2 does hit back in multilingual, so the answer changes if that is the part of the workload you care about most.

GLM-4.7 gives you the larger context window at 200K, compared with 128K for Mercury 2.

Quick Verdict

Pick GLM-4.7 if you want the stronger benchmark profile. Mercury 2 only becomes the better choice if multilingual is the priority.

Agentic

GLM-4.7

GLM-4.7

66.1

Mercury 2

63.7

67
Terminal-Bench 2.0
63
72
BrowseComp
67
61
OSWorld-Verified
62

Coding

GLM-4.7

GLM-4.7

46.6

Mercury 2

41.1

78
HumanEval
75
43
SWE-bench Verified
46
43
LiveCodeBench
38
51
SWE-bench Pro
43

Multimodal & Grounded

GLM-4.7

GLM-4.7

70.5

Mercury 2

68.3

66
MMMU-Pro
66
76
OfficeQA Pro
71

Reasoning

GLM-4.7

GLM-4.7

80.2

Mercury 2

80.1

82
SimpleQA
82
80
MuSR
82
84
BBH
87
79
LongBench v2
77
78
MRCRv2
76

Knowledge

GLM-4.7

GLM-4.7

61.8

Mercury 2

57.2

86
MMLU
78
84
GPQA
78
82
SuperGPQA
76
80
OpenBookQA
74
74
MMLU-Pro
72
16
HLE
9
72
FrontierScience
69

Instruction Following

GLM-4.7

GLM-4.7

85

Mercury 2

84

85
IFEval
84

Multilingual

Mercury 2

GLM-4.7

79.1

Mercury 2

79.7

81
MGSM
81
78
MMLU-ProX
79

Mathematics

GLM-4.7

GLM-4.7

85

Mercury 2

80.9

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

Frequently Asked Questions

Which is better, GLM-4.7 or Mercury 2?

GLM-4.7 is ahead overall, 67 to 65. The biggest single separator in this matchup is SWE-bench Pro, where the scores are 51 and 43.

Which is better for knowledge tasks, GLM-4.7 or Mercury 2?

GLM-4.7 has the edge for knowledge tasks in this comparison, averaging 61.8 versus 57.2. Inside this category, MMLU is the benchmark that creates the most daylight between them.

Which is better for coding, GLM-4.7 or Mercury 2?

GLM-4.7 has the edge for coding in this comparison, averaging 46.6 versus 41.1. Inside this category, SWE-bench Pro is the benchmark that creates the most daylight between them.

Which is better for math, GLM-4.7 or Mercury 2?

GLM-4.7 has the edge for math in this comparison, averaging 85 versus 80.9. Inside this category, AIME 2023 is the benchmark that creates the most daylight between them.

Which is better for reasoning, GLM-4.7 or Mercury 2?

GLM-4.7 has the edge for reasoning in this comparison, averaging 80.2 versus 80.1. Inside this category, BBH is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, GLM-4.7 or Mercury 2?

GLM-4.7 has the edge for agentic tasks in this comparison, averaging 66.1 versus 63.7. Inside this category, BrowseComp is the benchmark that creates the most daylight between them.

Which is better for multimodal and grounded tasks, GLM-4.7 or Mercury 2?

GLM-4.7 has the edge for multimodal and grounded tasks in this comparison, averaging 70.5 versus 68.3. Inside this category, OfficeQA Pro is the benchmark that creates the most daylight between them.

Which is better for instruction following, GLM-4.7 or Mercury 2?

GLM-4.7 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, GLM-4.7 or Mercury 2?

Mercury 2 has the edge for multilingual tasks in this comparison, averaging 79.7 versus 79.1. 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.