Head-to-head comparison across 2benchmark categories. Overall scores shown here use BenchLM's provisional ranking lane.
Mellum2-12B-A2.5B-Thinking
59
ZAYA1-8B
57
Pick Mellum2-12B-A2.5B-Thinking if you want the stronger benchmark profile. ZAYA1-8B only becomes the better choice if knowledge is the priority or you need the larger 131K context window.
Knowledge
+15.5 difference
Inst. Following
+2.5 difference
Mellum2-12B-A2.5B-Thinking
ZAYA1-8B
N/A
$0 / $0
N/A
N/A
N/A
N/A
128K
131K
Pick Mellum2-12B-A2.5B-Thinking if you want the stronger benchmark profile. ZAYA1-8B only becomes the better choice if knowledge is the priority or you need the larger 131K context window.
Mellum2-12B-A2.5B-Thinking has the cleaner provisional overall profile here, landing at 59 versus 57. It is a real lead, but still close enough that category-level strengths matter more than the headline number.
Mellum2-12B-A2.5B-Thinking's sharpest advantage is in instruction following, where it averages 76.5 against 74. The single biggest benchmark swing on the page is GPQA, 57.6% to 71%. ZAYA1-8B does hit back in knowledge, so the answer changes if that is the part of the workload you care about most.
ZAYA1-8B gives you the larger context window at 131K, compared with 128K for Mellum2-12B-A2.5B-Thinking.
Mellum2-12B-A2.5B-Thinking is ahead on BenchLM's provisional leaderboard, 59 to 57. The biggest single separator in this matchup is GPQA, where the scores are 57.6% and 71%.
ZAYA1-8B has the edge for knowledge tasks in this comparison, averaging 73.1 versus 57.6. Inside this category, GPQA is the benchmark that creates the most daylight between them.
Mellum2-12B-A2.5B-Thinking has the edge for instruction following in this comparison, averaging 76.5 versus 74. Inside this category, IFEval is the benchmark that creates the most daylight between them.
For engineers, researchers, and the plain curious — a weekly brief on new models, ranking shifts, and pricing changes.
Free. No spam. Unsubscribe anytime.