Model comparison
DeepSeek-R1-Distill-Qwen-32B vs Qwen3.5-9B
DeepSeek-R1-Distill-Qwen-32B is the stronger model overall, scoring 35.5 to 33.8 on the Noometry Index.
Last verified . 4 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- They share 4 benchmarks with published results for both. DeepSeek-R1-Distill-Qwen-32B scores higher in 2 categories and Qwen3.5-9B in 3 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where DeepSeek-R1-Distill-Qwen-32B leads 28.1 to 14.5.
- The biggest single-benchmark swing is GPQA Diamond: 64.1% for DeepSeek-R1-Distill-Qwen-32B and 79% for Qwen3.5-9B.
Side by side
| DeepSeek-R1-Distill-Qwen-32B | Qwen3.5-9B | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 35.5 | 33.8 |
| Released | 2025-01-20 | 2026-02-23 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 66K |
| Input $ / M tokens | — | $0.10 |
| Output $ / M tokens | — | $0.15 |
| Results tracked | 14 | 10 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
DeepSeek-R1-Distill-Qwen-32B: 36.1 (#212), Qwen3.5-9B: 35.9 (#217)
| Benchmark | DeepSeek-R1-Distill-Qwen-32B | Qwen3.5-9B |
|---|---|---|
| SciCode | — | 27.5% |
| BigCodeBench Instruct | 43.9% | — |
| LiveBench Coding | 33.7% | — |
| BigCodeBench Complete | 54.9% | — |
Agentic & Tool Use DeepSeek-R1-Distill-Qwen-32B leads
DeepSeek-R1-Distill-Qwen-32B: 28.1 (#94), Qwen3.5-9B: 14.5 (#151)
| Benchmark | DeepSeek-R1-Distill-Qwen-32B | Qwen3.5-9B |
|---|---|---|
| Terminal-Bench | — | 9.2% |
| BALROG | 19.5% | — |
Reasoning Qwen3.5-9B leads
DeepSeek-R1-Distill-Qwen-32B: 18.2 (#284), Qwen3.5-9B: 23.1 (#182)
| Benchmark | DeepSeek-R1-Distill-Qwen-32B | Qwen3.5-9B |
|---|---|---|
| Chess Puzzles | 1% | 12% |
| Epoch Capabilities Index | 137.44 | 139.46 |
| CritPt | — | 0.3% |
| LiveBench Reasoning | 52.3% | — |
| DTBench | — | 71.2% |
| LiveBench Data Analysis | 45.4% | — |
| LMCA | — | 24.5% |
| LiveBench | 45.5% | — |
Math Too close to call
DeepSeek-R1-Distill-Qwen-32B: 34.5 (#194), Qwen3.5-9B: 34.8 (#192)
| Benchmark | DeepSeek-R1-Distill-Qwen-32B | Qwen3.5-9B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 55.6% | 61.7% |
| MathArena Final-Answer Competitions | — | 48.5% |
| LiveBench Math | 59.4% | — |
Knowledge Qwen3.5-9B leads
DeepSeek-R1-Distill-Qwen-32B: 35.7 (#182), Qwen3.5-9B: 46.0 (#84)
| Benchmark | DeepSeek-R1-Distill-Qwen-32B | Qwen3.5-9B |
|---|---|---|
| GPQA Diamond | 64.1% | 79% |
Instruction Following Not comparable
DeepSeek-R1-Distill-Qwen-32B: 61.6 (#243), Qwen3.5-9B: —
| Benchmark | DeepSeek-R1-Distill-Qwen-32B | Qwen3.5-9B |
|---|---|---|
| LiveBench Instruction Following | 55.7% | — |
Writing & Preference Not comparable
DeepSeek-R1-Distill-Qwen-32B: 49.6 (#188), Qwen3.5-9B: —
| Benchmark | DeepSeek-R1-Distill-Qwen-32B | Qwen3.5-9B |
|---|---|---|
| LiveBench Language | 26.8% | — |
Frequently asked questions
Is DeepSeek-R1-Distill-Qwen-32B better than Qwen3.5-9B?
DeepSeek-R1-Distill-Qwen-32B is the stronger model overall, scoring 35.5 to 33.8 on the Noometry Index.
Is DeepSeek-R1-Distill-Qwen-32B or Qwen3.5-9B better for coding?
They score almost the same on coding (36.1 vs 35.9); test both on your own repository before choosing.
How many benchmarks do DeepSeek-R1-Distill-Qwen-32B and Qwen3.5-9B share?
4 benchmarks have published results for both models. DeepSeek-R1-Distill-Qwen-32B has 14 scored results on Noometry and Qwen3.5-9B has 10.