Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
Qwen2.5-1M 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.
Qwen2.5-1M's sharpest advantage is in coding, where it averages 44.8 against 41.1. The single biggest benchmark swing on the page is SWE-bench Pro, 49 to 43.
Mercury 2 is the reasoning model in the pair, while Qwen2.5-1M 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. Qwen2.5-1M gives you the larger context window at 1M, compared with 128K for Mercury 2.
Pick Qwen2.5-1M if you want the stronger benchmark profile. Mercury 2 only becomes the better choice if you want the stronger reasoning-first profile.
Qwen2.5-1M
64.7
Mercury 2
63.7
Qwen2.5-1M
44.8
Mercury 2
41.1
Qwen2.5-1M
68.4
Mercury 2
68.3
Qwen2.5-1M
80.9
Mercury 2
80.1
Qwen2.5-1M
60.4
Mercury 2
57.2
Qwen2.5-1M
84
Mercury 2
84
Qwen2.5-1M
80.4
Mercury 2
79.7
Qwen2.5-1M
83.6
Mercury 2
80.9
Qwen2.5-1M is ahead overall, 66 to 65. The biggest single separator in this matchup is SWE-bench Pro, where the scores are 49 and 43.
Qwen2.5-1M has the edge for knowledge tasks in this comparison, averaging 60.4 versus 57.2. Inside this category, MMLU is the benchmark that creates the most daylight between them.
Qwen2.5-1M has the edge for coding in this comparison, averaging 44.8 versus 41.1. Inside this category, SWE-bench Pro is the benchmark that creates the most daylight between them.
Qwen2.5-1M has the edge for math in this comparison, averaging 83.6 versus 80.9. Inside this category, AIME 2023 is the benchmark that creates the most daylight between them.
Qwen2.5-1M has the edge for reasoning in this comparison, averaging 80.9 versus 80.1. Inside this category, BBH is the benchmark that creates the most daylight between them.
Qwen2.5-1M has the edge for agentic tasks in this comparison, averaging 64.7 versus 63.7. Inside this category, BrowseComp is the benchmark that creates the most daylight between them.
Qwen2.5-1M has the edge for multimodal and grounded tasks in this comparison, averaging 68.4 versus 68.3. Inside this category, OfficeQA Pro is the benchmark that creates the most daylight between them.
Qwen2.5-1M and Mercury 2 are effectively tied for instruction following here, both landing at 84 on average.
Qwen2.5-1M has the edge for multilingual tasks in this comparison, averaging 80.4 versus 79.7. Inside this category, MMLU-ProX 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.