Model comparison
Deepseek Coder v2 vs Phi 3 Medium 4k Instruct
Deepseek Coder v2 is the stronger model overall, scoring 35.3 to 32.4 on the Noometry Index.
Last verified . 17 shared benchmarks.
DeepSeek
MicrosoftSummary
- They share 17 benchmarks with published results for both. Deepseek Coder v2 scores higher in 8 categories and Phi 3 Medium 4k Instruct in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Deepseek Coder v2 leads 36.4 to 30.8.
Side by side
| Deepseek Coder v2 | Phi 3 Medium 4k Instruct | |
|---|---|---|
| Provider | DeepSeek | Microsoft |
| Noometry Index | 35.3 | 32.4 |
| Released | 2024-06-17 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 24 | 17 |
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 3 Medium 4k Instruct: 32.3 (#263)
| Benchmark | Deepseek Coder v2 | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Coding | 1251 | 1130 |
| BigCodeBench Instruct | 48.2% | — |
| BigCodeBench Complete | 59.7% | — |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |
Reasoning Deepseek Coder v2 leads
Deepseek Coder v2: 22.6 (#175), Phi 3 Medium 4k Instruct: 20.8 (#214)
| Benchmark | Deepseek Coder v2 | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Hard Prompts | 1207 | 1127 |
| WinoGrande | 83.7% | — |
Math Deepseek Coder v2 leads
Deepseek Coder v2: 32.3 (#188), Phi 3 Medium 4k Instruct: 30.9 (#202)
| Benchmark | Deepseek Coder v2 | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Math | 1241 | 1173 |
| GSM8K | 94.5% | — |
Knowledge Deepseek Coder v2 leads
Deepseek Coder v2: 31.7 (#209), Phi 3 Medium 4k Instruct: 29.6 (#226)
| Benchmark | Deepseek Coder v2 | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Expert | 1181 | 1108 |
| ARC (AI2) Challenge | 64.3% | — |
Multilingual Deepseek Coder v2 leads
Deepseek Coder v2: 36.4 (#235), Phi 3 Medium 4k Instruct: 30.8 (#258)
| Benchmark | Deepseek Coder v2 | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Non-English | 1182 | 1094 |
| LMArena Chinese | 1201 | 1108 |
| LMArena French | 1184 | 1109 |
| LMArena German | 1164 | 1101 |
| LMArena Japanese | 1126 | 1042 |
| LMArena Korean | 1104 | 954 |
| LMArena Russian | 1188 | 1145 |
| LMArena Spanish | 1153 | 1095 |
Instruction Following Deepseek Coder v2 leads
Deepseek Coder v2: 61.9 (#237), Phi 3 Medium 4k Instruct: 57.8 (#263)
| Benchmark | Deepseek Coder v2 | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Instruction Following | 1180 | 1114 |
Long Context Deepseek Coder v2 leads
Deepseek Coder v2: 37.0 (#219), Phi 3 Medium 4k Instruct: 33.9 (#250)
| Benchmark | Deepseek Coder v2 | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Longer Query | 1219 | 1120 |
Writing & Preference Deepseek Coder v2 leads
Deepseek Coder v2: 38.4 (#249), Phi 3 Medium 4k Instruct: 34.3 (#267)
| Benchmark | Deepseek Coder v2 | Phi 3 Medium 4k Instruct |
|---|---|---|
| LMArena Text | 1191 | 1138 |
| LMArena Creative Writing | 1120 | 1106 |
| LMArena Multi-Turn | 1176 | 1088 |
Frequently asked questions
Is Deepseek Coder v2 better than Phi 3 Medium 4k Instruct?
Deepseek Coder v2 is the stronger model overall, scoring 35.3 to 32.4 on the Noometry Index.
Is Deepseek Coder v2 or Phi 3 Medium 4k Instruct better for coding?
Deepseek Coder v2 scores higher on coding benchmarks: 37.5 versus 32.3 in the Noometry coding category.
How many benchmarks do Deepseek Coder v2 and Phi 3 Medium 4k Instruct share?
17 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and Phi 3 Medium 4k Instruct has 17.