Model comparison
DeepSeek-R1-Distill-Qwen-32B vs Qwen3.5 397B-A17B
Qwen3.5 397B-A17B is the stronger model overall, scoring 46.0 to 35.5 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 0 categories and Qwen3.5 397B-A17B in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.5 397B-A17B leads 53.3 to 35.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 55.6% for DeepSeek-R1-Distill-Qwen-32B and 88.9% for Qwen3.5 397B-A17B.
Side by side
| DeepSeek-R1-Distill-Qwen-32B | Qwen3.5 397B-A17B | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 35.5 | 46.0 |
| Released | 2025-01-20 | 2026-02-01 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 66K |
| Input $ / M tokens | — | $0.60 |
| Output $ / M tokens | — | $3.60 |
| Results tracked | 14 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.5 397B-A17B leads
DeepSeek-R1-Distill-Qwen-32B: 36.1 (#212), Qwen3.5 397B-A17B: 42.0 (#114)
| Benchmark | DeepSeek-R1-Distill-Qwen-32B | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena WebDev | — | 1400 |
| BigCodeBench Instruct | 43.9% | — |
| LiveBench Coding | 33.7% | — |
| LMArena Coding | — | 1465 |
| BigCodeBench Complete | 54.9% | — |
Agentic & Tool Use Qwen3.5 397B-A17B leads
DeepSeek-R1-Distill-Qwen-32B: 28.1 (#94), Qwen3.5 397B-A17B: 33.3 (#53)
| Benchmark | DeepSeek-R1-Distill-Qwen-32B | Qwen3.5 397B-A17B |
|---|---|---|
| APEX-Agents | — | 24.9% |
| τ²-bench Airline | — | 81.5% |
| τ²-bench Banking | — | 9.8% |
| τ²-bench Retail | — | 84.4% |
| τ²-bench Telecom | — | 97.8% |
| BALROG | 19.5% | — |
Reasoning Qwen3.5 397B-A17B leads
DeepSeek-R1-Distill-Qwen-32B: 18.2 (#284), Qwen3.5 397B-A17B: 34.5 (#70)
| Benchmark | DeepSeek-R1-Distill-Qwen-32B | Qwen3.5 397B-A17B |
|---|---|---|
| Chess Puzzles | 1% | 13% |
| Epoch Capabilities Index | 137.44 | 146.65 |
| Kagi LLM Benchmark | — | 73.7% |
| NYT Connections (extended) | — | 58.9% |
| Thematic Generalization | — | 65.1% |
| LiveBench Reasoning | 52.3% | — |
| LMArena Hard Prompts | — | 1448 |
| Mystery Game Puzzles | — | 18% |
| DTBench | — | 87.5% |
| LiveBench Data Analysis | 45.4% | — |
| LMCA | — | 37.9% |
| LiveBench | 45.5% | — |
Math Qwen3.5 397B-A17B leads
DeepSeek-R1-Distill-Qwen-32B: 34.5 (#194), Qwen3.5 397B-A17B: 46.1 (#73)
| Benchmark | DeepSeek-R1-Distill-Qwen-32B | Qwen3.5 397B-A17B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 55.6% | 88.9% |
| FrontierMath (Tiers 1-3) | — | 31.2% |
| LiveBench Math | 59.4% | — |
| LMArena Math | — | 1454 |
Knowledge Qwen3.5 397B-A17B leads
DeepSeek-R1-Distill-Qwen-32B: 35.7 (#182), Qwen3.5 397B-A17B: 53.3 (#58)
| Benchmark | DeepSeek-R1-Distill-Qwen-32B | Qwen3.5 397B-A17B |
|---|---|---|
| GPQA Diamond | 64.1% | 86.4% |
| LMArena Expert | — | 1462 |
Multimodal Not comparable
DeepSeek-R1-Distill-Qwen-32B: —, Qwen3.5 397B-A17B: 40.7 (#44)
| Benchmark | DeepSeek-R1-Distill-Qwen-32B | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Vision | — | 1263 |
Multilingual Not comparable
DeepSeek-R1-Distill-Qwen-32B: —, Qwen3.5 397B-A17B: 53.7 (#59)
| Benchmark | DeepSeek-R1-Distill-Qwen-32B | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Non-English | — | 1430 |
| LMArena Chinese | — | 1500 |
| LMArena French | — | 1461 |
| LMArena German | — | 1447 |
| LMArena Japanese | — | 1426 |
| LMArena Korean | — | 1384 |
| LMArena Russian | — | 1429 |
| LMArena Spanish | — | 1441 |
Instruction Following Qwen3.5 397B-A17B leads
DeepSeek-R1-Distill-Qwen-32B: 61.6 (#243), Qwen3.5 397B-A17B: 75.0 (#77)
| Benchmark | DeepSeek-R1-Distill-Qwen-32B | Qwen3.5 397B-A17B |
|---|---|---|
| LiveBench Instruction Following | 55.7% | — |
| LMArena Instruction Following | — | 1424 |
Long Context Not comparable
DeepSeek-R1-Distill-Qwen-32B: —, Qwen3.5 397B-A17B: 44.1 (#74)
| Benchmark | DeepSeek-R1-Distill-Qwen-32B | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Longer Query | — | 1442 |
Writing & Preference Qwen3.5 397B-A17B leads
DeepSeek-R1-Distill-Qwen-32B: 49.6 (#188), Qwen3.5 397B-A17B: 62.3 (#79)
| Benchmark | DeepSeek-R1-Distill-Qwen-32B | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Text | — | 1438 |
| LMArena Creative Writing | — | 1401 |
| EQ-Bench Creative Writing | — | 1478 |
| LMArena Multi-Turn | — | 1446 |
| LiveBench Language | 26.8% | — |
Frequently asked questions
Is DeepSeek-R1-Distill-Qwen-32B better than Qwen3.5 397B-A17B?
Qwen3.5 397B-A17B is the stronger model overall, scoring 46.0 to 35.5 on the Noometry Index.
Is DeepSeek-R1-Distill-Qwen-32B or Qwen3.5 397B-A17B better for coding?
Qwen3.5 397B-A17B scores higher on coding benchmarks: 42.0 versus 36.1 in the Noometry coding category.
How many benchmarks do DeepSeek-R1-Distill-Qwen-32B and Qwen3.5 397B-A17B share?
4 benchmarks have published results for both models. DeepSeek-R1-Distill-Qwen-32B has 14 scored results on Noometry and Qwen3.5 397B-A17B has 36.