Head-to-head comparison across 3benchmark categories. Overall scores shown here use BenchLM's provisional ranking lane.
Gemma 4 31B
64
Qwen3.6-35B-A3B
66
Verified leaderboard positions: Gemma 4 31B unranked · Qwen3.6-35B-A3B #23
Pick Qwen3.6-35B-A3B if you want the stronger benchmark profile. Gemma 4 31B only becomes the better choice if multimodal & grounded is the priority.
Coding
+25.3 difference
Knowledge
+0.8 difference
Multimodal
+0.8 difference
Gemma 4 31B
Qwen3.6-35B-A3B
$0 / $0
N/A
N/A
N/A
N/A
N/A
256K
262K
Pick Qwen3.6-35B-A3B if you want the stronger benchmark profile. Gemma 4 31B only becomes the better choice if multimodal & grounded is the priority.
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 41.6. The single biggest benchmark swing on the page is HLE, 26.5% to 21.4%. Gemma 4 31B does hit back in multimodal & grounded, so the answer changes if that is the part of the workload you care about most.
Qwen3.6-35B-A3B gives you the larger context window at 262K, compared with 256K for Gemma 4 31B.
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 26.5% and 21.4%.
Gemma 4 31B has the edge for knowledge tasks in this comparison, averaging 61.3 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 41.6. Inside this category, AA-SciCode is the benchmark that creates the most daylight between them.
Gemma 4 31B has the edge for multimodal and grounded tasks in this comparison, averaging 76.9 versus 76.1. Inside this category, MMMU-Pro is the benchmark that creates the most daylight between them.
Estimates at 50,000 req/day · 1000 tokens/req average.
For engineers, researchers, and the plain curious — a weekly brief on new models, ranking shifts, and pricing changes.
Free. No spam. Unsubscribe anytime.