Model comparison
Deepseek Coder v2 vs Phi-4 Mini
Deepseek Coder v2 is the stronger model overall, scoring 35.3 to 30.4 on the Noometry Index.
Last verified . 0 shared benchmarks.
DeepSeek
MicrosoftSummary
- The widest gap is in coding, where Deepseek Coder v2 leads 37.5 to 27.6.
Side by side
| Deepseek Coder v2 | Phi-4 Mini | |
|---|---|---|
| Provider | DeepSeek | Microsoft |
| Noometry Index | 35.3 | 30.4 |
| Released | 2024-06-17 | 2024-12-11 |
| Weights | Open | Open |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $0.075 |
| Output $ / M tokens | — | $0.30 |
| Results tracked | 24 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Deepseek Coder v2 leads
Deepseek Coder v2: 37.5 (#178), Phi-4 Mini: 27.6 (#312)
| Benchmark | Deepseek Coder v2 | Phi-4 Mini |
|---|---|---|
| SciCode | — | 10.8% |
| BigCodeBench Instruct | 48.2% | — |
| LMArena Coding | 1251 | — |
| BigCodeBench Complete | 59.7% | — |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |
Reasoning Too close to call
Deepseek Coder v2: 22.6 (#175), Phi-4 Mini: 21.7 (#190)
| Benchmark | Deepseek Coder v2 | Phi-4 Mini |
|---|---|---|
| CritPt | — | 0% |
| LMArena Hard Prompts | 1207 | — |
| WinoGrande | 83.7% | — |
Math Not comparable
Deepseek Coder v2: 32.3 (#188), Phi-4 Mini: —
| Benchmark | Deepseek Coder v2 | Phi-4 Mini |
|---|---|---|
| LMArena Math | 1241 | — |
| GSM8K | 94.5% | — |
Knowledge Deepseek Coder v2 leads
Deepseek Coder v2: 31.7 (#209), Phi-4 Mini: 24.8 (#261)
| Benchmark | Deepseek Coder v2 | Phi-4 Mini |
|---|---|---|
| Vectara Hallucination Rate | — | 23.5% |
| LMArena Expert | 1181 | — |
| ARC (AI2) Challenge | 64.3% | — |
Multilingual Not comparable
Deepseek Coder v2: 36.4 (#235), Phi-4 Mini: —
| Benchmark | Deepseek Coder v2 | Phi-4 Mini |
|---|---|---|
| LMArena Non-English | 1182 | — |
| LMArena Chinese | 1201 | — |
| LMArena French | 1184 | — |
| LMArena German | 1164 | — |
| LMArena Japanese | 1126 | — |
| LMArena Korean | 1104 | — |
| LMArena Russian | 1188 | — |
| LMArena Spanish | 1153 | — |
Instruction Following Not comparable
Deepseek Coder v2: 61.9 (#237), Phi-4 Mini: —
| Benchmark | Deepseek Coder v2 | Phi-4 Mini |
|---|---|---|
| LMArena Instruction Following | 1180 | — |
Long Context Not comparable
Deepseek Coder v2: 37.0 (#219), Phi-4 Mini: —
| Benchmark | Deepseek Coder v2 | Phi-4 Mini |
|---|---|---|
| LMArena Longer Query | 1219 | — |
Writing & Preference Not comparable
Deepseek Coder v2: 38.4 (#249), Phi-4 Mini: —
| Benchmark | Deepseek Coder v2 | Phi-4 Mini |
|---|---|---|
| LMArena Text | 1191 | — |
| LMArena Creative Writing | 1120 | — |
| LMArena Multi-Turn | 1176 | — |
Frequently asked questions
Is Deepseek Coder v2 better than Phi-4 Mini?
Deepseek Coder v2 is the stronger model overall, scoring 35.3 to 30.4 on the Noometry Index.
Is Deepseek Coder v2 or Phi-4 Mini better for coding?
Deepseek Coder v2 scores higher on coding benchmarks: 37.5 versus 27.6 in the Noometry coding category.
How many benchmarks do Deepseek Coder v2 and Phi-4 Mini share?
0 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Phi-4 Mini has 3.