Verdict
DeepSeek-R1-Distill-Qwen-32B leads 6–0 across 7 shared benchmarks.
DeepSeek-R1-Distill-Qwen-14B 0 · DeepSeek-R1-Distill-Qwen-32B 6 · 1 tied · higher isn't always better — check the caveats below.
Reported scores — protocols may differ. How we compare
Math: DeepSeek-R1-Distill-Qwen-32B leads 3–0 across 3 shared math benchmarks (largest gap: OTIS Mock AIME 2024-2025, 55.51 vs 50.51 — protocols undisclosed).
Coding: DeepSeek-R1-Distill-Qwen-32B leads 2–0 across 2 shared coding benchmarks (largest gap: Codeforces rating, 1691 vs 1481 — single evaluator).
Vendor claims — compare against the measured scores above. A claim is what a developer says about its own model, not an independent measurement.
Reasoning
“Notably, our distilled 14B model outperforms state-of-the-art open-source QwQ-32B-Preview by a large margin…”
Reasoning
“Using Qwen2.5-32B as the base model, direct distillation from DeepSeek-R1 outperforms applying RL on it.”
DeepSeek-R1-Distill-Qwen-32B leads 6–0 across 7 shared benchmarks. DeepSeek-R1-Distill-Qwen-14B leads 0 benchmarks and DeepSeek-R1-Distill-Qwen-32B leads 6, with 1 tied. Higher isn't always better — see the integrity caveats on each benchmark.
DeepSeek-R1-Distill-Qwen-14B and DeepSeek-R1-Distill-Qwen-32B have 7 benchmarks in common in our data — those are the only rows where a direct, apples-to-apples comparison is drawn.
DeepSeek-R1-Distill-Qwen-32B leads math 3–0. DeepSeek-R1-Distill-Qwen-32B leads coding 2–0.