Mercury 2 vs GLM-4.7-Flash

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

Mercury 2 has the cleaner overall profile here, landing at 65 versus 62. It is a real lead, but still close enough that category-level strengths matter more than the headline number.

Mercury 2's sharpest advantage is in reasoning, where it averages 80.1 against 69.7. The single biggest benchmark swing on the page is MuSR, 82 to 61. GLM-4.7-Flash does hit back in coding, so the answer changes if that is the part of the workload you care about most.

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

Quick Verdict

Pick Mercury 2 if you want the stronger benchmark profile. GLM-4.7-Flash only becomes the better choice if coding is the priority or you need the larger 200K context window.

Agentic

Mercury 2

Mercury 2

63.7

GLM-4.7-Flash

61.3

63
Terminal-Bench 2.0
64
67
BrowseComp
63
62
OSWorld-Verified
57

Coding

GLM-4.7-Flash

Mercury 2

41.1

GLM-4.7-Flash

45.9

75
HumanEval
58
46
SWE-bench Verified
40
38
LiveCodeBench
45
43
SWE-bench Pro
48

Multimodal & Grounded

Mercury 2

Mercury 2

68.3

GLM-4.7-Flash

62.5

66
MMMU-Pro
58
71
OfficeQA Pro
68

Reasoning

Mercury 2

Mercury 2

80.1

GLM-4.7-Flash

69.7

82
SimpleQA
63
82
MuSR
61
87
BBH
86
77
LongBench v2
72
76
MRCRv2
76

Knowledge

Mercury 2

Mercury 2

57.2

GLM-4.7-Flash

54.1

78
MMLU
66
78
GPQA
65
76
SuperGPQA
63
74
OpenBookQA
61
72
MMLU-Pro
74
9
HLE
15
69
FrontierScience
63

Instruction Following

Tie

Mercury 2

84

GLM-4.7-Flash

84

84
IFEval
84

Multilingual

GLM-4.7-Flash

Mercury 2

79.7

GLM-4.7-Flash

81.8

81
MGSM
85
79
MMLU-ProX
80

Mathematics

Mercury 2

Mercury 2

80.9

GLM-4.7-Flash

74

81
AIME 2023
66
83
AIME 2024
68
82
AIME 2025
67
77
HMMT Feb 2023
62
79
HMMT Feb 2024
64
78
HMMT Feb 2025
63
80
BRUMO 2025
65
82
MATH-500
85

Frequently Asked Questions

Which is better, Mercury 2 or GLM-4.7-Flash?

Mercury 2 is ahead overall, 65 to 62. The biggest single separator in this matchup is MuSR, where the scores are 82 and 61.

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

Mercury 2 has the edge for knowledge tasks in this comparison, averaging 57.2 versus 54.1. Inside this category, GPQA is the benchmark that creates the most daylight between them.

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

GLM-4.7-Flash has the edge for coding in this comparison, averaging 45.9 versus 41.1. Inside this category, HumanEval is the benchmark that creates the most daylight between them.

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

Mercury 2 has the edge for math in this comparison, averaging 80.9 versus 74. Inside this category, AIME 2023 is the benchmark that creates the most daylight between them.

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

Mercury 2 has the edge for reasoning in this comparison, averaging 80.1 versus 69.7. Inside this category, MuSR is the benchmark that creates the most daylight between them.

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

Mercury 2 has the edge for agentic tasks in this comparison, averaging 63.7 versus 61.3. 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 GLM-4.7-Flash?

Mercury 2 has the edge for multimodal and grounded tasks in this comparison, averaging 68.3 versus 62.5. Inside this category, MMMU-Pro is the benchmark that creates the most daylight between them.

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

Mercury 2 and GLM-4.7-Flash are effectively tied for instruction following here, both landing at 84 on average.

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

GLM-4.7-Flash has the edge for multilingual tasks in this comparison, averaging 81.8 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.