Mercury 2 vs MiniMax M2.5

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

Mercury 2 is clearly ahead on the aggregate, 65 to 59. 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 69.6. The single biggest benchmark swing on the page is MuSR, 82 to 68. MiniMax M2.5 does hit back in multilingual, so the answer changes if that is the part of the workload you care about most.

MiniMax M2.5 is also the more expensive model on tokens at $0.30 input / $1.20 output per 1M tokens, versus $0.25 input / $0.75 output per 1M tokens for Mercury 2. Mercury 2 is the reasoning model in the pair, while MiniMax M2.5 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.

Quick Verdict

Pick Mercury 2 if you want the stronger benchmark profile. MiniMax M2.5 only becomes the better choice if multilingual is the priority or you would rather avoid the extra latency and token burn of a reasoning model.

Agentic

Mercury 2

Mercury 2

63.7

MiniMax M2.5

53.4

63
Terminal-Bench 2.0
51
67
BrowseComp
62
62
OSWorld-Verified
50

Coding

Mercury 2

Mercury 2

41.1

MiniMax M2.5

38.7

75
HumanEval
65
46
SWE-bench Verified
45
38
LiveCodeBench
35
43
SWE-bench Pro
41

Multimodal & Grounded

Mercury 2

Mercury 2

68.3

MiniMax M2.5

62

66
MMMU-Pro
57
71
OfficeQA Pro
68

Reasoning

Mercury 2

Mercury 2

80.1

MiniMax M2.5

69.6

82
SimpleQA
70
82
MuSR
68
87
BBH
83
77
LongBench v2
66
76
MRCRv2
69

Knowledge

Mercury 2

Mercury 2

57.2

MiniMax M2.5

55.3

78
MMLU
73
78
GPQA
72
76
SuperGPQA
70
74
OpenBookQA
68
72
MMLU-Pro
73
9
HLE
10
69
FrontierScience
66

Instruction Following

MiniMax M2.5

Mercury 2

84

MiniMax M2.5

85

84
IFEval
85

Multilingual

MiniMax M2.5

Mercury 2

79.7

MiniMax M2.5

82.1

81
MGSM
84
79
MMLU-ProX
81

Mathematics

Mercury 2

Mercury 2

80.9

MiniMax M2.5

76.1

81
AIME 2023
73
83
AIME 2024
75
82
AIME 2025
74
77
HMMT Feb 2023
69
79
HMMT Feb 2024
71
78
HMMT Feb 2025
70
80
BRUMO 2025
72
82
MATH-500
81

Frequently Asked Questions

Which is better, Mercury 2 or MiniMax M2.5?

Mercury 2 is ahead overall, 65 to 59. The biggest single separator in this matchup is MuSR, where the scores are 82 and 68.

Which is better for knowledge tasks, Mercury 2 or MiniMax M2.5?

Mercury 2 has the edge for knowledge tasks in this comparison, averaging 57.2 versus 55.3. Inside this category, GPQA is the benchmark that creates the most daylight between them.

Which is better for coding, Mercury 2 or MiniMax M2.5?

Mercury 2 has the edge for coding in this comparison, averaging 41.1 versus 38.7. Inside this category, HumanEval is the benchmark that creates the most daylight between them.

Which is better for math, Mercury 2 or MiniMax M2.5?

Mercury 2 has the edge for math in this comparison, averaging 80.9 versus 76.1. Inside this category, AIME 2023 is the benchmark that creates the most daylight between them.

Which is better for reasoning, Mercury 2 or MiniMax M2.5?

Mercury 2 has the edge for reasoning in this comparison, averaging 80.1 versus 69.6. Inside this category, MuSR is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, Mercury 2 or MiniMax M2.5?

Mercury 2 has the edge for agentic tasks in this comparison, averaging 63.7 versus 53.4. 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 MiniMax M2.5?

Mercury 2 has the edge for multimodal and grounded tasks in this comparison, averaging 68.3 versus 62. Inside this category, MMMU-Pro is the benchmark that creates the most daylight between them.

Which is better for instruction following, Mercury 2 or MiniMax M2.5?

MiniMax M2.5 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, Mercury 2 or MiniMax M2.5?

MiniMax M2.5 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.