Head-to-head comparison across 3benchmark categories. Overall scores shown here use BenchLM's provisional ranking lane.
DeepSeek V4 Pro Base
43
Qwen3.5 397B
64
Verified leaderboard positions: DeepSeek V4 Pro Base unranked · Qwen3.5 397B #14
Pick Qwen3.5 397B if you want the stronger benchmark profile. DeepSeek V4 Pro Base only becomes the better choice if you need the larger 1M context window.
Reasoning
+11.7 difference
Knowledge
+1.8 difference
Multilingual
+0.3 difference
DeepSeek V4 Pro Base
Qwen3.5 397B
$null / $null
$0.6 / $3.6
N/A
96 t/s
N/A
2.44s
1M
128K
Pick Qwen3.5 397B if you want the stronger benchmark profile. DeepSeek V4 Pro Base only becomes the better choice if you need the larger 1M context window.
Qwen3.5 397B is clearly ahead on the provisional aggregate, 64 to 43. 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 reasoning, where it averages 63.2 against 51.5. The single biggest benchmark swing on the page is SuperGPQA, 53.9% to 70.4%.
DeepSeek V4 Pro Base gives you the larger context window at 1M, compared with 128K for Qwen3.5 397B.
Qwen3.5 397B is ahead on BenchLM's provisional leaderboard, 64 to 43. The biggest single separator in this matchup is SuperGPQA, where the scores are 53.9% and 70.4%.
Qwen3.5 397B has the edge for knowledge tasks in this comparison, averaging 65.2 versus 63.4. Inside this category, SuperGPQA is the benchmark that creates the most daylight between them.
Qwen3.5 397B has the edge for reasoning in this comparison, averaging 63.2 versus 51.5. Inside this category, LongBench v2 is the benchmark that creates the most daylight between them.
Qwen3.5 397B has the edge for multilingual tasks in this comparison, averaging 84.7 versus 84.4. DeepSeek V4 Pro Base stays close enough that the answer can still flip depending on your workload.
For engineers, researchers, and the plain curious — a weekly brief on new models, ranking shifts, and pricing changes.
Free. No spam. Unsubscribe anytime.