o1-preview vs Mercury 2

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

o1-preview is clearly ahead on the aggregate, 77 to 65. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

o1-preview's sharpest advantage is in coding, where it averages 64.6 against 41.1. The single biggest benchmark swing on the page is SWE-bench Pro, 69 to 43.

o1-preview gives you the larger context window at 200K, compared with 128K for Mercury 2.

Quick Verdict

Pick o1-preview if you want the stronger benchmark profile. Mercury 2 only becomes the better choice if its workflow or ecosystem matters more than the raw scoreboard.

Agentic

o1-preview

o1-preview

75.4

Mercury 2

63.7

77
Terminal-Bench 2.0
63
79
BrowseComp
67
71
OSWorld-Verified
62

Coding

o1-preview

o1-preview

64.6

Mercury 2

41.1

86
HumanEval
75
65
SWE-bench Verified
46
60
LiveCodeBench
38
69
SWE-bench Pro
43

Multimodal & Grounded

o1-preview

o1-preview

75.6

Mercury 2

68.3

72
MMMU-Pro
66
80
OfficeQA Pro
71

Reasoning

o1-preview

o1-preview

86.8

Mercury 2

80.1

88
SimpleQA
82
86
MuSR
82
93
BBH
87
87
LongBench v2
77
83
MRCRv2
76

Knowledge

o1-preview

o1-preview

71.3

Mercury 2

57.2

92
MMLU
78
90
GPQA
78
88
SuperGPQA
76
86
OpenBookQA
74
80
MMLU-Pro
72
32
HLE
9
83
FrontierScience
69

Instruction Following

o1-preview

o1-preview

88

Mercury 2

84

88
IFEval
84

Multilingual

o1-preview

o1-preview

87.4

Mercury 2

79.7

90
MGSM
81
86
MMLU-ProX
79

Mathematics

o1-preview

o1-preview

93.5

Mercury 2

80.9

94
AIME 2023
81
96
AIME 2024
83
95
AIME 2025
82
90
HMMT Feb 2023
77
92
HMMT Feb 2024
79
91
HMMT Feb 2025
78
93
BRUMO 2025
80
94
MATH-500
82

Frequently Asked Questions

Which is better, o1-preview or Mercury 2?

o1-preview is ahead overall, 77 to 65. The biggest single separator in this matchup is SWE-bench Pro, where the scores are 69 and 43.

Which is better for knowledge tasks, o1-preview or Mercury 2?

o1-preview has the edge for knowledge tasks in this comparison, averaging 71.3 versus 57.2. Inside this category, HLE is the benchmark that creates the most daylight between them.

Which is better for coding, o1-preview or Mercury 2?

o1-preview has the edge for coding in this comparison, averaging 64.6 versus 41.1. Inside this category, SWE-bench Pro is the benchmark that creates the most daylight between them.

Which is better for math, o1-preview or Mercury 2?

o1-preview has the edge for math in this comparison, averaging 93.5 versus 80.9. Inside this category, AIME 2023 is the benchmark that creates the most daylight between them.

Which is better for reasoning, o1-preview or Mercury 2?

o1-preview has the edge for reasoning in this comparison, averaging 86.8 versus 80.1. Inside this category, LongBench v2 is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, o1-preview or Mercury 2?

o1-preview has the edge for agentic tasks in this comparison, averaging 75.4 versus 63.7. 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, o1-preview or Mercury 2?

o1-preview has the edge for multimodal and grounded tasks in this comparison, averaging 75.6 versus 68.3. Inside this category, OfficeQA Pro is the benchmark that creates the most daylight between them.

Which is better for instruction following, o1-preview or Mercury 2?

o1-preview has the edge for instruction following in this comparison, averaging 88 versus 84. Inside this category, IFEval is the benchmark that creates the most daylight between them.

Which is better for multilingual tasks, o1-preview or Mercury 2?

o1-preview has the edge for multilingual tasks in this comparison, averaging 87.4 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.