Model comparison
DeepSeek-R1-Distill-Qwen-14B vs Qwen3.6 27B
Qwen3.6 27B is the stronger model overall, scoring 42.2 to 32.7 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-14B scores higher in 0 categories and Qwen3.6 27B in 4 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.6 27B leads 52.4 to 24.1.
- The biggest single-benchmark swing is GPQA Diamond: 44.7% for DeepSeek-R1-Distill-Qwen-14B and 85.9% for Qwen3.6 27B.
Side by side
| DeepSeek-R1-Distill-Qwen-14B | Qwen3.6 27B | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 32.7 | 42.2 |
| Released | 2025-01-20 | 2026-04-22 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 66K |
| Input $ / M tokens | — | $0.60 |
| Output $ / M tokens | — | $3.60 |
| Results tracked | 7 | 11 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.6 27B leads
DeepSeek-R1-Distill-Qwen-14B: 36.9 (#200), Qwen3.6 27B: 39.1 (#163)
| Benchmark | DeepSeek-R1-Distill-Qwen-14B | Qwen3.6 27B |
|---|---|---|
| SciCode | — | 37.3% |
| BigCodeBench Instruct | 38.1% | — |
| BigCodeBench Complete | 48.4% | — |
Reasoning Qwen3.6 27B leads
DeepSeek-R1-Distill-Qwen-14B: 19.2 (#263), Qwen3.6 27B: 25.0 (#153)
| Benchmark | DeepSeek-R1-Distill-Qwen-14B | Qwen3.6 27B |
|---|---|---|
| Chess Puzzles | 1% | 22% |
| Epoch Capabilities Index | 135.43 | 146.5 |
| CritPt | — | 0.9% |
| Mystery Game Puzzles | — | 7% |
| DTBench | — | 78.1% |
| LMCA | — | 34.5% |
Math Qwen3.6 27B leads
DeepSeek-R1-Distill-Qwen-14B: 35.5 (#184), Qwen3.6 27B: 48.5 (#62)
| Benchmark | DeepSeek-R1-Distill-Qwen-14B | Qwen3.6 27B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 50.6% | 91.1% |
| FrontierMath (Tiers 1-3) | — | 35.1% |
| MATH Level 5 | 87.1% | — |
Knowledge Qwen3.6 27B leads
DeepSeek-R1-Distill-Qwen-14B: 24.1 (#270), Qwen3.6 27B: 52.4 (#63)
| Benchmark | DeepSeek-R1-Distill-Qwen-14B | Qwen3.6 27B |
|---|---|---|
| GPQA Diamond | 44.7% | 85.9% |
Writing & Preference Not comparable
DeepSeek-R1-Distill-Qwen-14B: —, Qwen3.6 27B: 50.3 (#181)
| Benchmark | DeepSeek-R1-Distill-Qwen-14B | Qwen3.6 27B |
|---|---|---|
| EQ-Bench 4 | — | 1026 |
Frequently asked questions
Is DeepSeek-R1-Distill-Qwen-14B better than Qwen3.6 27B?
Qwen3.6 27B is the stronger model overall, scoring 42.2 to 32.7 on the Noometry Index.
Is DeepSeek-R1-Distill-Qwen-14B or Qwen3.6 27B better for coding?
Qwen3.6 27B scores higher on coding benchmarks: 39.1 versus 36.9 in the Noometry coding category.
How many benchmarks do DeepSeek-R1-Distill-Qwen-14B and Qwen3.6 27B share?
4 benchmarks have published results for both models. DeepSeek-R1-Distill-Qwen-14B has 7 scored results on Noometry and Qwen3.6 27B has 11.