Side-by-side benchmark comparison across agentic, coding, multimodal, knowledge, reasoning, and math workflows.
Seed-2.0-Mini is clearly ahead on the aggregate, 53 to 47. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Seed-2.0-Mini's sharpest advantage is in multimodal & grounded, where it averages 73.1 against 50.5. The single biggest benchmark swing on the page is MMMU-Pro, 74 to 46. Z-1 does hit back in coding, so the answer changes if that is the part of the workload you care about most.
Seed-2.0-Mini gives you the larger context window at 256K, compared with 128K for Z-1.
Pick Seed-2.0-Mini if you want the stronger benchmark profile. Z-1 only becomes the better choice if coding is the priority.
Seed-2.0-Mini
46.2
Z-1
42.2
Seed-2.0-Mini
24.7
Z-1
26.7
Seed-2.0-Mini
73.1
Z-1
50.5
Seed-2.0-Mini
64.8
Z-1
54.8
Seed-2.0-Mini
44.6
Z-1
42.7
Seed-2.0-Mini
80
Z-1
80
Seed-2.0-Mini
71.8
Z-1
72.7
Seed-2.0-Mini
65.1
Z-1
60.9
Seed-2.0-Mini is ahead overall, 53 to 47. The biggest single separator in this matchup is MMMU-Pro, where the scores are 74 and 46.
Seed-2.0-Mini has the edge for knowledge tasks in this comparison, averaging 44.6 versus 42.7. Inside this category, MMLU is the benchmark that creates the most daylight between them.
Z-1 has the edge for coding in this comparison, averaging 26.7 versus 24.7. Inside this category, HumanEval is the benchmark that creates the most daylight between them.
Seed-2.0-Mini has the edge for math in this comparison, averaging 65.1 versus 60.9. Inside this category, AIME 2023 is the benchmark that creates the most daylight between them.
Seed-2.0-Mini has the edge for reasoning in this comparison, averaging 64.8 versus 54.8. Inside this category, MRCRv2 is the benchmark that creates the most daylight between them.
Seed-2.0-Mini has the edge for agentic tasks in this comparison, averaging 46.2 versus 42.2. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.
Seed-2.0-Mini has the edge for multimodal and grounded tasks in this comparison, averaging 73.1 versus 50.5. Inside this category, MMMU-Pro is the benchmark that creates the most daylight between them.
Seed-2.0-Mini and Z-1 are effectively tied for instruction following here, both landing at 80 on average.
Z-1 has the edge for multilingual tasks in this comparison, averaging 72.7 versus 71.8. 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.