Model comparison
DeepSeek-R1-Distill-Qwen-32B vs Phi-4 Mini
DeepSeek-R1-Distill-Qwen-32B is the stronger model overall, scoring 35.5 to 30.9 on the Noometry Index.
Last verified . 0 shared benchmarks.
DeepSeek
MicrosoftSummary
- The widest gap is in knowledge, where DeepSeek-R1-Distill-Qwen-32B leads 35.7 to 25.3.
Side by side
| DeepSeek-R1-Distill-Qwen-32B | Phi-4 Mini | |
|---|---|---|
| Provider | DeepSeek | Microsoft |
| Noometry Index | 35.5 | 30.9 |
| Released | 2025-01-20 | 2024-12-11 |
| Weights | Open | Open |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $0.075 |
| Output $ / M tokens | — | $0.30 |
| Results tracked | 14 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-R1-Distill-Qwen-32B leads
DeepSeek-R1-Distill-Qwen-32B: 36.1 (#212), Phi-4 Mini: 28.1 (#317)
| Benchmark | DeepSeek-R1-Distill-Qwen-32B | Phi-4 Mini |
|---|---|---|
| SciCode | — | 10.8% |
| BigCodeBench Instruct | 43.9% | — |
| LiveBench Coding | 33.7% | — |
| BigCodeBench Complete | 54.9% | — |
Agentic & Tool Use Not comparable
DeepSeek-R1-Distill-Qwen-32B: 28.1 (#94), Phi-4 Mini: —
| Benchmark | DeepSeek-R1-Distill-Qwen-32B | Phi-4 Mini |
|---|---|---|
| BALROG | 19.5% | — |
Reasoning Phi-4 Mini leads
DeepSeek-R1-Distill-Qwen-32B: 18.2 (#284), Phi-4 Mini: 22.4 (#195)
| Benchmark | DeepSeek-R1-Distill-Qwen-32B | Phi-4 Mini |
|---|---|---|
| CritPt | — | 0% |
| Chess Puzzles | 1% | — |
| LiveBench Reasoning | 52.3% | — |
| LiveBench Data Analysis | 45.4% | — |
| Epoch Capabilities Index | 137.44 | — |
| LiveBench | 45.5% | — |
Math Not comparable
DeepSeek-R1-Distill-Qwen-32B: 34.5 (#194), Phi-4 Mini: —
| Benchmark | DeepSeek-R1-Distill-Qwen-32B | Phi-4 Mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 55.6% | — |
| LiveBench Math | 59.4% | — |
Knowledge DeepSeek-R1-Distill-Qwen-32B leads
DeepSeek-R1-Distill-Qwen-32B: 35.7 (#182), Phi-4 Mini: 25.3 (#262)
| Benchmark | DeepSeek-R1-Distill-Qwen-32B | Phi-4 Mini |
|---|---|---|
| GPQA Diamond | 64.1% | — |
| Vectara Hallucination Rate | — | 23.5% |
Instruction Following Not comparable
DeepSeek-R1-Distill-Qwen-32B: 61.6 (#243), Phi-4 Mini: —
| Benchmark | DeepSeek-R1-Distill-Qwen-32B | Phi-4 Mini |
|---|---|---|
| LiveBench Instruction Following | 55.7% | — |
Writing & Preference Not comparable
DeepSeek-R1-Distill-Qwen-32B: 49.6 (#188), Phi-4 Mini: —
| Benchmark | DeepSeek-R1-Distill-Qwen-32B | Phi-4 Mini |
|---|---|---|
| LiveBench Language | 26.8% | — |
Frequently asked questions
Is DeepSeek-R1-Distill-Qwen-32B better than Phi-4 Mini?
DeepSeek-R1-Distill-Qwen-32B is the stronger model overall, scoring 35.5 to 30.9 on the Noometry Index.
Is DeepSeek-R1-Distill-Qwen-32B or Phi-4 Mini better for coding?
DeepSeek-R1-Distill-Qwen-32B scores higher on coding benchmarks: 36.1 versus 28.1 in the Noometry coding category.
How many benchmarks do DeepSeek-R1-Distill-Qwen-32B and Phi-4 Mini share?
0 benchmarks have published results for both models. DeepSeek-R1-Distill-Qwen-32B has 14 scored results on Noometry and Phi-4 Mini has 3.