Head-to-head comparison across 4benchmark categories. Overall scores shown here use BenchLM's provisional ranking lane.
Muse Spark
82
Qwen3.5-35B-A3B
56
Verified leaderboard positions: Muse Spark unranked · Qwen3.5-35B-A3B #20
Pick Muse Spark if you want the stronger benchmark profile. Qwen3.5-35B-A3B only becomes the better choice if knowledge is the priority.
Agentic
+8.4 difference
Coding
+3.3 difference
Reasoning
+16.5 difference
Knowledge
+28.9 difference
Muse Spark
Qwen3.5-35B-A3B
N/A
$0 / $0
N/A
N/A
N/A
N/A
262K
262K
Pick Muse Spark if you want the stronger benchmark profile. Qwen3.5-35B-A3B only becomes the better choice if knowledge is the priority.
Muse Spark is clearly ahead on the provisional aggregate, 82 to 56. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
Muse Spark's sharpest advantage is in agentic, where it averages 59 against 50.6. The single biggest benchmark swing on the page is Terminal-Bench 2.0, 59% to 40.5%. Qwen3.5-35B-A3B does hit back in knowledge, so the answer changes if that is the part of the workload you care about most.
Muse Spark is ahead on BenchLM's provisional leaderboard, 82 to 56. The biggest single separator in this matchup is Terminal-Bench 2.0, where the scores are 59% and 40.5%.
Qwen3.5-35B-A3B has the edge for knowledge tasks in this comparison, averaging 79.3 versus 50.4. Inside this category, AA-Omniscience Index is the benchmark that creates the most daylight between them.
Muse Spark has the edge for coding in this comparison, averaging 61.7 versus 58.4. Inside this category, Terminal-Bench Hard is the benchmark that creates the most daylight between them.
Qwen3.5-35B-A3B has the edge for reasoning in this comparison, averaging 59 versus 42.5. Inside this category, CritPt is the benchmark that creates the most daylight between them.
Muse Spark has the edge for agentic tasks in this comparison, averaging 59 versus 50.6. Inside this category, GDPval-AA 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.