Head-to-head comparison across 3benchmark categories. Overall scores shown here use BenchLM's provisional ranking lane.
DeepSeek V4 Pro (Max)
87
Qwen3.5 397B
64
Verified leaderboard positions: DeepSeek V4 Pro (Max) #2 · Qwen3.5 397B #14
Pick DeepSeek V4 Pro (Max) if you want the stronger benchmark profile. Qwen3.5 397B only becomes the better choice if you would rather avoid the extra latency and token burn of a reasoning model.
Agentic
+17.8 difference
Coding
+15.6 difference
Knowledge
+0.9 difference
DeepSeek V4 Pro (Max)
Qwen3.5 397B
$1.74 / $3.48
$0.6 / $3.6
N/A
96 t/s
N/A
2.44s
1M
128K
Pick DeepSeek V4 Pro (Max) if you want the stronger benchmark profile. Qwen3.5 397B only becomes the better choice if you would rather avoid the extra latency and token burn of a reasoning model.
DeepSeek V4 Pro (Max) is clearly ahead on the provisional aggregate, 87 to 64. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
DeepSeek V4 Pro (Max)'s sharpest advantage is in agentic, where it averages 74 against 56.2. The single biggest benchmark swing on the page is BrowseComp, 83.4% to 62%.
Qwen3.5 397B is also the more expensive model on tokens at $0.60 input / $3.60 output per 1M tokens, versus $1.74 input / $3.48 output per 1M tokens for DeepSeek V4 Pro (Max). DeepSeek V4 Pro (Max) 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. DeepSeek V4 Pro (Max) gives you the larger context window at 1M, compared with 128K for Qwen3.5 397B.
DeepSeek V4 Pro (Max) is ahead on BenchLM's provisional leaderboard, 87 to 64. The biggest single separator in this matchup is BrowseComp, where the scores are 83.4% and 62%.
DeepSeek V4 Pro (Max) has the edge for knowledge tasks in this comparison, averaging 66.1 versus 65.2. Inside this category, HLE is the benchmark that creates the most daylight between them.
DeepSeek V4 Pro (Max) has the edge for coding in this comparison, averaging 75.9 versus 60.3. Inside this category, SWE-bench Pro is the benchmark that creates the most daylight between them.
DeepSeek V4 Pro (Max) has the edge for agentic tasks in this comparison, averaging 74 versus 56.2. Inside this category, MCP Atlas 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.