Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
DeepSeek V3.2 (Thinking) is clearly ahead on the aggregate, 70 to 65. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
DeepSeek V3.2 (Thinking)'s sharpest advantage is in coding, where it averages 51.2 against 41.1. The single biggest benchmark swing on the page is SWE-bench Pro, 58 to 43.
Pick DeepSeek V3.2 (Thinking) 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.
DeepSeek V3.2 (Thinking)
69.4
Mercury 2
63.7
DeepSeek V3.2 (Thinking)
51.2
Mercury 2
41.1
DeepSeek V3.2 (Thinking)
71
Mercury 2
68.3
DeepSeek V3.2 (Thinking)
80.6
Mercury 2
80.1
DeepSeek V3.2 (Thinking)
64.4
Mercury 2
57.2
DeepSeek V3.2 (Thinking)
85
Mercury 2
84
DeepSeek V3.2 (Thinking)
80.8
Mercury 2
79.7
DeepSeek V3.2 (Thinking)
85.1
Mercury 2
80.9
DeepSeek V3.2 (Thinking) is ahead overall, 70 to 65. The biggest single separator in this matchup is SWE-bench Pro, where the scores are 58 and 43.
DeepSeek V3.2 (Thinking) has the edge for knowledge tasks in this comparison, averaging 64.4 versus 57.2. Inside this category, HLE is the benchmark that creates the most daylight between them.
DeepSeek V3.2 (Thinking) has the edge for coding in this comparison, averaging 51.2 versus 41.1. Inside this category, SWE-bench Pro is the benchmark that creates the most daylight between them.
DeepSeek V3.2 (Thinking) has the edge for math in this comparison, averaging 85.1 versus 80.9. Inside this category, AIME 2023 is the benchmark that creates the most daylight between them.
DeepSeek V3.2 (Thinking) has the edge for reasoning in this comparison, averaging 80.6 versus 80.1. Inside this category, MRCRv2 is the benchmark that creates the most daylight between them.
DeepSeek V3.2 (Thinking) has the edge for agentic tasks in this comparison, averaging 69.4 versus 63.7. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.
DeepSeek V3.2 (Thinking) has the edge for multimodal and grounded tasks in this comparison, averaging 71 versus 68.3. Inside this category, OfficeQA Pro is the benchmark that creates the most daylight between them.
DeepSeek V3.2 (Thinking) 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.
DeepSeek V3.2 (Thinking) has the edge for multilingual tasks in this comparison, averaging 80.8 versus 79.7. Inside this category, MGSM is the benchmark that creates the most daylight between them.
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.