Model comparison
DeepSeek Coder 6.7B vs Phi 3 Mini 4k Instruct
Phi 3 Mini 4k Instruct has enough public results to be ranked (#328); DeepSeek Coder 6.7B does not yet, so treat this comparison as directional.
Last verified . 5 shared benchmarks.
DeepSeek
MicrosoftSummary
- They share 5 benchmarks with published results for both. DeepSeek Coder 6.7B scores higher in 1 category and Phi 3 Mini 4k Instruct in 0 categories; one gap is clear of the uncertainty.
- The widest gap is in coding, where DeepSeek Coder 6.7B leads 35.8 to 26.6.
Side by side
| DeepSeek Coder 6.7B | Phi 3 Mini 4k Instruct | |
|---|---|---|
| Provider | DeepSeek | Microsoft |
| Noometry Index | 37.6 | 27.9 |
| Released | 2023-11-02 | 2024-04-23 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 9 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek Coder 6.7B leads
DeepSeek Coder 6.7B: 35.8 (#219), Phi 3 Mini 4k Instruct: 26.6 (#323)
| Benchmark | DeepSeek Coder 6.7B | Phi 3 Mini 4k Instruct |
|---|---|---|
| HumanEval+ | 71.3% | 59.1% |
| MBPP+ | 65.6% | 54.2% |
| BigCodeBench Instruct | 35.5% | — |
| LiveBench Coding | — | 15.5% |
| LMArena Coding | — | 1093 |
| BigCodeBench Complete | 43.8% | — |
Reasoning Not comparable
DeepSeek Coder 6.7B: —, Phi 3 Mini 4k Instruct: 14.1 (#328)
| Benchmark | DeepSeek Coder 6.7B | Phi 3 Mini 4k Instruct |
|---|---|---|
| WinoGrande | 57.6% | 70.8% |
| Chess Puzzles | — | 0% |
| LiveBench Reasoning | — | 26.8% |
| LMArena Hard Prompts | — | 1072 |
| LiveBench Data Analysis | — | 34.7% |
| Adversarial NLI | — | 52.8% |
| BIG-Bench Hard | — | 71.7% |
| Epoch Capabilities Index | 89.62 | — |
| HellaSwag | — | 76.7% |
| LiveBench | — | 22.4% |
Math Not comparable
DeepSeek Coder 6.7B: —, Phi 3 Mini 4k Instruct: 26.6 (#257)
| Benchmark | DeepSeek Coder 6.7B | Phi 3 Mini 4k Instruct |
|---|---|---|
| LiveBench Math | — | 15.7% |
| LMArena Math | — | 1111 |
| GSM8K | 21.3% | — |
Knowledge Not comparable
DeepSeek Coder 6.7B: —, Phi 3 Mini 4k Instruct: 28.5 (#246)
| Benchmark | DeepSeek Coder 6.7B | Phi 3 Mini 4k Instruct |
|---|---|---|
| ARC (AI2) Challenge | 36.4% | 84.9% |
| MMLU | 36.4% | 68.8% |
| LMArena Expert | — | 1045 |
| OpenBookQA | — | 88% |
| TriviaQA | — | 64% |
Multilingual Not comparable
DeepSeek Coder 6.7B: —, Phi 3 Mini 4k Instruct: 26.3 (#280)
| Benchmark | DeepSeek Coder 6.7B | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Non-English | — | 1021 |
| LMArena Chinese | — | 1021 |
| LMArena French | — | 1076 |
| LMArena German | — | 1044 |
| LMArena Japanese | — | 935 |
| LMArena Korean | — | 905 |
| LMArena Russian | — | 1022 |
| LMArena Spanish | — | 1085 |
Instruction Following Not comparable
DeepSeek Coder 6.7B: —, Phi 3 Mini 4k Instruct: 47.7 (#303)
| Benchmark | DeepSeek Coder 6.7B | Phi 3 Mini 4k Instruct |
|---|---|---|
| LiveBench Instruction Following | — | 39.1% |
| LMArena Instruction Following | — | 1053 |
Long Context Not comparable
DeepSeek Coder 6.7B: —, Phi 3 Mini 4k Instruct: 31.7 (#276)
| Benchmark | DeepSeek Coder 6.7B | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Longer Query | — | 1044 |
Writing & Preference Not comparable
DeepSeek Coder 6.7B: —, Phi 3 Mini 4k Instruct: 27.6 (#300)
| Benchmark | DeepSeek Coder 6.7B | Phi 3 Mini 4k Instruct |
|---|---|---|
| LMArena Text | — | 1073 |
| LMArena Creative Writing | — | 1037 |
| LMArena Multi-Turn | — | 1018 |
| LiveBench Language | — | 9.2% |
Frequently asked questions
Is DeepSeek Coder 6.7B better than Phi 3 Mini 4k Instruct?
Phi 3 Mini 4k Instruct has enough public results to be ranked (#328); DeepSeek Coder 6.7B does not yet, so treat this comparison as directional.
Is DeepSeek Coder 6.7B or Phi 3 Mini 4k Instruct better for coding?
DeepSeek Coder 6.7B scores higher on coding benchmarks: 35.8 versus 26.6 in the Noometry coding category.
How many benchmarks do DeepSeek Coder 6.7B and Phi 3 Mini 4k Instruct share?
5 benchmarks have published results for both models. DeepSeek Coder 6.7B has 9 scored results on Noometry and Phi 3 Mini 4k Instruct has 35.