GLM-5 vs Mercury 2

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

GLM-5 and Mercury 2 finish on the same overall score, so this is less about a single winner and more about where the edge shows up. The headline says tie; the benchmark table is where the real choice happens.

Mercury 2's sharpest advantage is in coding, where it averages 41.1 against 41.1. The single biggest benchmark swing on the page is MMLU, 88 to 78. GLM-5 does hit back in knowledge, 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 GLM-5 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. GLM-5 gives you the larger context window at 200K, compared with 128K for Mercury 2.

Quick Verdict

Treat this as a split decision. GLM-5 makes more sense if knowledge is the priority or you need the larger 200K context window; Mercury 2 is the better fit if agentic is the priority or you want the stronger reasoning-first profile.

Agentic

Mercury 2

GLM-5

62.3

Mercury 2

63.7

63
Terminal-Bench 2.0
63
67
BrowseComp
67
58
OSWorld-Verified
62

Coding

Tie

GLM-5

41.1

Mercury 2

41.1

80
HumanEval
75
46
SWE-bench Verified
46
35
LiveCodeBench
38
46
SWE-bench Pro
43

Multimodal & Grounded

GLM-5

GLM-5

69.2

Mercury 2

68.3

66
MMMU-Pro
66
73
OfficeQA Pro
71

Reasoning

Mercury 2

GLM-5

79.4

Mercury 2

80.1

84
SimpleQA
82
82
MuSR
82
83
BBH
87
77
LongBench v2
77
73
MRCRv2
76

Knowledge

GLM-5

GLM-5

62.1

Mercury 2

57.2

88
MMLU
78
86
GPQA
78
84
SuperGPQA
76
82
OpenBookQA
74
74
MMLU-Pro
72
13
HLE
9
74
FrontierScience
69

Instruction Following

GLM-5

GLM-5

85

Mercury 2

84

85
IFEval
84

Multilingual

GLM-5

GLM-5

82.1

Mercury 2

79.7

84
MGSM
81
81
MMLU-ProX
79

Mathematics

GLM-5

GLM-5

84.8

Mercury 2

80.9

88
AIME 2023
81
90
AIME 2024
83
89
AIME 2025
82
84
HMMT Feb 2023
77
86
HMMT Feb 2024
79
85
HMMT Feb 2025
78
87
BRUMO 2025
80
82
MATH-500
82

Frequently Asked Questions

Which is better, GLM-5 or Mercury 2?

GLM-5 and Mercury 2 are tied on overall score, so the right pick depends on which category matters most for your use case.

Which is better for knowledge tasks, GLM-5 or Mercury 2?

GLM-5 has the edge for knowledge tasks in this comparison, averaging 62.1 versus 57.2. Inside this category, MMLU is the benchmark that creates the most daylight between them.

Which is better for coding, GLM-5 or Mercury 2?

GLM-5 and Mercury 2 are effectively tied for coding here, both landing at 41.1 on average.

Which is better for math, GLM-5 or Mercury 2?

GLM-5 has the edge for math in this comparison, averaging 84.8 versus 80.9. Inside this category, AIME 2023 is the benchmark that creates the most daylight between them.

Which is better for reasoning, GLM-5 or Mercury 2?

Mercury 2 has the edge for reasoning in this comparison, averaging 80.1 versus 79.4. Inside this category, BBH is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, GLM-5 or Mercury 2?

Mercury 2 has the edge for agentic tasks in this comparison, averaging 63.7 versus 62.3. Inside this category, OSWorld-Verified is the benchmark that creates the most daylight between them.

Which is better for multimodal and grounded tasks, GLM-5 or Mercury 2?

GLM-5 has the edge for multimodal and grounded tasks in this comparison, averaging 69.2 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-5 or Mercury 2?

GLM-5 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-5 or Mercury 2?

GLM-5 has the edge for multilingual tasks in this comparison, averaging 82.1 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.