Mercury 2 vs Qwen3.5 397B

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

Mercury 2 has the cleaner overall profile here, landing at 65 versus 62. It is a real lead, but still close enough that category-level strengths matter more than the headline number.

Mercury 2's sharpest advantage is in multimodal & grounded, where it averages 68.3 against 61.4. The single biggest benchmark swing on the page is OSWorld-Verified, 62 to 52. Qwen3.5 397B does hit back in knowledge, 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 $0.00 input / $0.00 output per 1M tokens for Qwen3.5 397B. That is roughly Infinityx on output cost alone. Mercury 2 is the reasoning model in the pair, while Qwen3.5 397B 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. Qwen3.5 397B only becomes the better choice if knowledge is the priority or you want the cheaper token bill.

Agentic

Mercury 2

Mercury 2

63.7

Qwen3.5 397B

56.9

63
Terminal-Bench 2.0
58
67
BrowseComp
62
62
OSWorld-Verified
52

Coding

Mercury 2

Mercury 2

41.1

Qwen3.5 397B

40.7

75
HumanEval
75
46
SWE-bench Verified
42
38
LiveCodeBench
39
43
SWE-bench Pro
42

Multimodal & Grounded

Mercury 2

Mercury 2

68.3

Qwen3.5 397B

61.4

66
MMMU-Pro
56
71
OfficeQA Pro
68

Reasoning

Mercury 2

Mercury 2

80.1

Qwen3.5 397B

75.9

82
SimpleQA
80
82
MuSR
78
87
BBH
82
77
LongBench v2
72
76
MRCRv2
71

Knowledge

Qwen3.5 397B

Mercury 2

57.2

Qwen3.5 397B

59.3

78
MMLU
83
78
GPQA
82
76
SuperGPQA
80
74
OpenBookQA
78
72
MMLU-Pro
73
9
HLE
10
69
FrontierScience
71

Instruction Following

Mercury 2

Mercury 2

84

Qwen3.5 397B

82

84
IFEval
82

Multilingual

Mercury 2

Mercury 2

79.7

Qwen3.5 397B

78.8

81
MGSM
82
79
MMLU-ProX
77

Mathematics

Qwen3.5 397B

Mercury 2

80.9

Qwen3.5 397B

81.6

81
AIME 2023
83
83
AIME 2024
85
82
AIME 2025
84
77
HMMT Feb 2023
79
79
HMMT Feb 2024
81
78
HMMT Feb 2025
80
80
BRUMO 2025
82
82
MATH-500
81

Frequently Asked Questions

Which is better, Mercury 2 or Qwen3.5 397B?

Mercury 2 is ahead overall, 65 to 62. The biggest single separator in this matchup is OSWorld-Verified, where the scores are 62 and 52.

Which is better for knowledge tasks, Mercury 2 or Qwen3.5 397B?

Qwen3.5 397B has the edge for knowledge tasks in this comparison, averaging 59.3 versus 57.2. Inside this category, MMLU is the benchmark that creates the most daylight between them.

Which is better for coding, Mercury 2 or Qwen3.5 397B?

Mercury 2 has the edge for coding in this comparison, averaging 41.1 versus 40.7. Inside this category, SWE-bench Verified is the benchmark that creates the most daylight between them.

Which is better for math, Mercury 2 or Qwen3.5 397B?

Qwen3.5 397B has the edge for math in this comparison, averaging 81.6 versus 80.9. Inside this category, AIME 2023 is the benchmark that creates the most daylight between them.

Which is better for reasoning, Mercury 2 or Qwen3.5 397B?

Mercury 2 has the edge for reasoning in this comparison, averaging 80.1 versus 75.9. Inside this category, BBH is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, Mercury 2 or Qwen3.5 397B?

Mercury 2 has the edge for agentic tasks in this comparison, averaging 63.7 versus 56.9. Inside this category, OSWorld-Verified is the benchmark that creates the most daylight between them.

Which is better for multimodal and grounded tasks, Mercury 2 or Qwen3.5 397B?

Mercury 2 has the edge for multimodal and grounded tasks in this comparison, averaging 68.3 versus 61.4. Inside this category, MMMU-Pro is the benchmark that creates the most daylight between them.

Which is better for instruction following, Mercury 2 or Qwen3.5 397B?

Mercury 2 has the edge for instruction following in this comparison, averaging 84 versus 82. Inside this category, IFEval is the benchmark that creates the most daylight between them.

Which is better for multilingual tasks, Mercury 2 or Qwen3.5 397B?

Mercury 2 has the edge for multilingual tasks in this comparison, averaging 79.7 versus 78.8. 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.