Head-to-head comparison across 4benchmark categories. Overall scores shown here use BenchLM's provisional ranking lane.
Qwen3.5 397B
64
Qwen3.6-35B-A3B
66
Verified leaderboard positions: Qwen3.5 397B #18 · Qwen3.6-35B-A3B #23
Pick Qwen3.6-35B-A3B if you want the stronger benchmark profile. Qwen3.5 397B only becomes the better choice if agentic is the priority or you would rather avoid the extra latency and token burn of a reasoning model.
Agentic
+4.7 difference
Coding
+6.6 difference
Knowledge
+4.7 difference
Multimodal
+3.5 difference
Qwen3.5 397B
Qwen3.6-35B-A3B
$0.6 / $3.6
N/A
96 t/s
N/A
2.44s
N/A
128K
262K
Pick Qwen3.6-35B-A3B if you want the stronger benchmark profile. Qwen3.5 397B only becomes the better choice if agentic is the priority or you would rather avoid the extra latency and token burn of a reasoning model.
Qwen3.6-35B-A3B has the cleaner provisional overall profile here, landing at 66 versus 64. It is a real lead, but still close enough that category-level strengths matter more than the headline number.
Qwen3.6-35B-A3B's sharpest advantage is in coding, where it averages 66.9 against 60.3. The single biggest benchmark swing on the page is HLE, 28.7% to 21.4%. Qwen3.5 397B does hit back in agentic, so the answer changes if that is the part of the workload you care about most.
Qwen3.6-35B-A3B 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. Qwen3.6-35B-A3B gives you the larger context window at 262K, compared with 128K for Qwen3.5 397B.
Qwen3.6-35B-A3B is ahead on BenchLM's provisional leaderboard, 66 to 64. The biggest single separator in this matchup is HLE, where the scores are 28.7% and 21.4%.
Qwen3.5 397B has the edge for knowledge tasks in this comparison, averaging 65.2 versus 60.5. Inside this category, AA-Omniscience Hallucination Rate is the benchmark that creates the most daylight between them.
Qwen3.6-35B-A3B has the edge for coding in this comparison, averaging 66.9 versus 60.3. Inside this category, AA-SciCode is the benchmark that creates the most daylight between them.
Qwen3.5 397B has the edge for agentic tasks in this comparison, averaging 56.2 versus 51.5. Inside this category, GDPval-AA is the benchmark that creates the most daylight between them.
Qwen3.5 397B has the edge for multimodal and grounded tasks in this comparison, averaging 79.6 versus 76.1. Inside this category, AA-MMMU-Pro 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.