MiMo-V2-Flash vs Mercury 2

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

MiMo-V2-Flash 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.

MiMo-V2-Flash's sharpest advantage is in coding, where it averages 50 against 41.1. The single biggest benchmark swing on the page is MMMU-Pro, 78 to 66. Mercury 2 does hit back in reasoning, so the answer changes if that is the part of the workload you care about most.

Quick Verdict

Pick MiMo-V2-Flash if you want the stronger benchmark profile. Mercury 2 only becomes the better choice if reasoning is the priority.

Agentic

Mercury 2

MiMo-V2-Flash

61.8

Mercury 2

63.7

63
Terminal-Bench 2.0
63
65
BrowseComp
67
58
OSWorld-Verified
62

Coding

MiMo-V2-Flash

MiMo-V2-Flash

50

Mercury 2

41.1

71
HumanEval
75
45
SWE-bench Verified
46
49
LiveCodeBench
38
52
SWE-bench Pro
43

Multimodal & Grounded

MiMo-V2-Flash

MiMo-V2-Flash

75.8

Mercury 2

68.3

78
MMMU-Pro
66
73
OfficeQA Pro
71

Reasoning

Mercury 2

MiMo-V2-Flash

75.3

Mercury 2

80.1

76
SimpleQA
82
74
MuSR
82
85
BBH
87
74
LongBench v2
77
73
MRCRv2
76

Knowledge

MiMo-V2-Flash

MiMo-V2-Flash

58.8

Mercury 2

57.2

79
MMLU
78
78
GPQA
78
76
SuperGPQA
76
74
OpenBookQA
74
72
MMLU-Pro
72
14
HLE
9
71
FrontierScience
69

Instruction Following

Tie

MiMo-V2-Flash

84

Mercury 2

84

84
IFEval
84

Multilingual

Mercury 2

MiMo-V2-Flash

79.1

Mercury 2

79.7

83
MGSM
81
77
MMLU-ProX
79

Mathematics

MiMo-V2-Flash

MiMo-V2-Flash

83.4

Mercury 2

80.9

79
AIME 2023
81
81
AIME 2024
83
80
AIME 2025
82
75
HMMT Feb 2023
77
77
HMMT Feb 2024
79
76
HMMT Feb 2025
78
78
BRUMO 2025
80
90
MATH-500
82

Frequently Asked Questions

Which is better, MiMo-V2-Flash or Mercury 2?

MiMo-V2-Flash is ahead overall, 66 to 65. The biggest single separator in this matchup is MMMU-Pro, where the scores are 78 and 66.

Which is better for knowledge tasks, MiMo-V2-Flash or Mercury 2?

MiMo-V2-Flash has the edge for knowledge tasks in this comparison, averaging 58.8 versus 57.2. Inside this category, HLE is the benchmark that creates the most daylight between them.

Which is better for coding, MiMo-V2-Flash or Mercury 2?

MiMo-V2-Flash has the edge for coding in this comparison, averaging 50 versus 41.1. Inside this category, LiveCodeBench is the benchmark that creates the most daylight between them.

Which is better for math, MiMo-V2-Flash or Mercury 2?

MiMo-V2-Flash has the edge for math in this comparison, averaging 83.4 versus 80.9. Inside this category, MATH-500 is the benchmark that creates the most daylight between them.

Which is better for reasoning, MiMo-V2-Flash or Mercury 2?

Mercury 2 has the edge for reasoning in this comparison, averaging 80.1 versus 75.3. Inside this category, MuSR is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, MiMo-V2-Flash or Mercury 2?

Mercury 2 has the edge for agentic tasks in this comparison, averaging 63.7 versus 61.8. Inside this category, OSWorld-Verified is the benchmark that creates the most daylight between them.

Which is better for multimodal and grounded tasks, MiMo-V2-Flash or Mercury 2?

MiMo-V2-Flash has the edge for multimodal and grounded tasks in this comparison, averaging 75.8 versus 68.3. Inside this category, MMMU-Pro is the benchmark that creates the most daylight between them.

Which is better for instruction following, MiMo-V2-Flash or Mercury 2?

MiMo-V2-Flash and Mercury 2 are effectively tied for instruction following here, both landing at 84 on average.

Which is better for multilingual tasks, MiMo-V2-Flash or Mercury 2?

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