Mercury 2 vs GPT-4o mini

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

Mercury 2 is clearly ahead on the aggregate, 65 to 52. 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 49.4. The single biggest benchmark swing on the page is LongBench v2, 77 to 49. GPT-4o mini does hit back in coding, so the answer changes if that is the part of the workload you care about most.

Mercury 2 is also the more expensive model on tokens at $0.25 input / $0.75 output per 1M tokens, versus $0.15 input / $0.60 output per 1M tokens for GPT-4o mini. Mercury 2 is the reasoning model in the pair, while GPT-4o mini 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. GPT-4o mini only becomes the better choice if coding is the priority or you want the cheaper token bill.

Agentic

Mercury 2

Mercury 2

63.7

GPT-4o mini

50.9

63
Terminal-Bench 2.0
58
67
BrowseComp
49
62
OSWorld-Verified
44

Coding

GPT-4o mini

Mercury 2

41.1

GPT-4o mini

65

75
HumanEval
87.2
46
SWE-bench Verified
Coming soon
38
LiveCodeBench
Coming soon
43
SWE-bench Pro
65

Multimodal & Grounded

Mercury 2

Mercury 2

68.3

GPT-4o mini

60.2

66
MMMU-Pro
66
71
OfficeQA Pro
53

Reasoning

Mercury 2

Mercury 2

80.1

GPT-4o mini

49.4

82
SimpleQA
Coming soon
82
MuSR
Coming soon
87
BBH
Coming soon
77
LongBench v2
49
76
MRCRv2
50

Knowledge

GPT-4o mini

Mercury 2

57.2

GPT-4o mini

62

78
MMLU
82
78
GPQA
Coming soon
76
SuperGPQA
Coming soon
74
OpenBookQA
Coming soon
72
MMLU-Pro
Coming soon
9
HLE
Coming soon
69
FrontierScience
62

Instruction Following

Coming soon

Comparable scores for this category are coming soon. One or both models do not have sourced results here yet.

84
IFEval
Coming soon

Multilingual

Mercury 2

Mercury 2

79.7

GPT-4o mini

74.7

81
MGSM
87
79
MMLU-ProX
68

Mathematics

Coming soon

Comparable scores for this category are coming soon. One or both models do not have sourced results here yet.

81
AIME 2023
Coming soon
83
AIME 2024
Coming soon
82
AIME 2025
Coming soon
77
HMMT Feb 2023
Coming soon
79
HMMT Feb 2024
Coming soon
78
HMMT Feb 2025
Coming soon
80
BRUMO 2025
Coming soon
82
MATH-500
Coming soon

Frequently Asked Questions

Which is better, Mercury 2 or GPT-4o mini?

Mercury 2 is ahead overall, 65 to 52. The biggest single separator in this matchup is LongBench v2, where the scores are 77 and 49.

Which is better for knowledge tasks, Mercury 2 or GPT-4o mini?

GPT-4o mini has the edge for knowledge tasks in this comparison, averaging 62 versus 57.2. Inside this category, FrontierScience is the benchmark that creates the most daylight between them.

Which is better for coding, Mercury 2 or GPT-4o mini?

GPT-4o mini has the edge for coding in this comparison, averaging 65 versus 41.1. Inside this category, SWE-bench Pro is the benchmark that creates the most daylight between them.

Which is better for reasoning, Mercury 2 or GPT-4o mini?

Mercury 2 has the edge for reasoning in this comparison, averaging 80.1 versus 49.4. Inside this category, LongBench v2 is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, Mercury 2 or GPT-4o mini?

Mercury 2 has the edge for agentic tasks in this comparison, averaging 63.7 versus 50.9. Inside this category, BrowseComp is the benchmark that creates the most daylight between them.

Which is better for multimodal and grounded tasks, Mercury 2 or GPT-4o mini?

Mercury 2 has the edge for multimodal and grounded tasks in this comparison, averaging 68.3 versus 60.2. Inside this category, OfficeQA Pro is the benchmark that creates the most daylight between them.

Which is better for multilingual tasks, Mercury 2 or GPT-4o mini?

Mercury 2 has the edge for multilingual tasks in this comparison, averaging 79.7 versus 74.7. Inside this category, MMLU-ProX 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.