Head-to-head comparison across 3benchmark categories. Overall scores shown here use BenchLM's provisional ranking lane.
Mellum2-12B-A2.5B-Thinking
59
Qwen3.5 397B
63
Verified leaderboard positions: Mellum2-12B-A2.5B-Thinking unranked · Qwen3.5 397B #20
Pick Qwen3.5 397B if you want the stronger benchmark profile. Mellum2-12B-A2.5B-Thinking only becomes the better choice if coding is the priority or you want the stronger reasoning-first profile.
Coding
+9.6 difference
Knowledge
+7.6 difference
Inst. Following
+16.1 difference
Mellum2-12B-A2.5B-Thinking
Qwen3.5 397B
N/A
$0.6 / $3.6
N/A
96 t/s
N/A
2.44s
128K
128K
Pick Qwen3.5 397B if you want the stronger benchmark profile. Mellum2-12B-A2.5B-Thinking only becomes the better choice if coding is the priority or you want the stronger reasoning-first profile.
Qwen3.5 397B is clearly ahead on the provisional aggregate, 63 to 59. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Qwen3.5 397B's sharpest advantage is in instruction following, where it averages 92.6 against 76.5. The single biggest benchmark swing on the page is GPQA, 57.6% to 88.4%. Mellum2-12B-A2.5B-Thinking does hit back in coding, so the answer changes if that is the part of the workload you care about most.
Mellum2-12B-A2.5B-Thinking 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.
Qwen3.5 397B is ahead on BenchLM's provisional leaderboard, 63 to 59. The biggest single separator in this matchup is GPQA, where the scores are 57.6% and 88.4%.
Qwen3.5 397B has the edge for knowledge tasks in this comparison, averaging 65.2 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 coding in this comparison, averaging 69.9 versus 60.3. Qwen3.5 397B stays close enough that the answer can still flip depending on your workload.
Qwen3.5 397B has the edge for instruction following in this comparison, averaging 92.6 versus 76.5. 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.