Model comparison
DeepSeek Coder 6.7B vs Wizardlm 70b
Wizardlm 70b has enough public results to be ranked (#249); DeepSeek Coder 6.7B does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
DeepSeek
MicrosoftSummary
- The widest gap is in coding, where DeepSeek Coder 6.7B leads 35.8 to 31.4.
Side by side
| DeepSeek Coder 6.7B | Wizardlm 70b | |
|---|---|---|
| Provider | DeepSeek | Microsoft |
| Noometry Index | 37.6 | 33.0 |
| Released | 2023-11-02 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 9 | 12 |
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), Wizardlm 70b: 31.4 (#285)
| Benchmark | DeepSeek Coder 6.7B | Wizardlm 70b |
|---|---|---|
| BigCodeBench Instruct | 35.5% | — |
| LMArena Coding | — | 1081 |
| BigCodeBench Complete | 43.8% | — |
| HumanEval+ | 71.3% | — |
| MBPP+ | 65.6% | — |
Reasoning Not comparable
DeepSeek Coder 6.7B: —, Wizardlm 70b: 20.7 (#234)
| Benchmark | DeepSeek Coder 6.7B | Wizardlm 70b |
|---|---|---|
| LMArena Hard Prompts | — | 1079 |
| Epoch Capabilities Index | 89.62 | — |
| WinoGrande | 57.6% | — |
Math Not comparable
DeepSeek Coder 6.7B: —, Wizardlm 70b: 32.2 (#218)
| Benchmark | DeepSeek Coder 6.7B | Wizardlm 70b |
|---|---|---|
| LMArena Math | — | 1116 |
| GSM8K | 21.3% | — |
Knowledge Not comparable
DeepSeek Coder 6.7B: —, Wizardlm 70b: —
| Benchmark | DeepSeek Coder 6.7B | Wizardlm 70b |
|---|---|---|
| ARC (AI2) Challenge | 36.4% | — |
| MMLU | 36.4% | — |
Multilingual Not comparable
DeepSeek Coder 6.7B: —, Wizardlm 70b: 29.6 (#265)
| Benchmark | DeepSeek Coder 6.7B | Wizardlm 70b |
|---|---|---|
| LMArena Non-English | — | 1078 |
| LMArena Chinese | — | 1052 |
| LMArena German | — | 1083 |
| LMArena Russian | — | 1155 |
Instruction Following Not comparable
DeepSeek Coder 6.7B: —, Wizardlm 70b: 56.3 (#273)
| Benchmark | DeepSeek Coder 6.7B | Wizardlm 70b |
|---|---|---|
| LMArena Instruction Following | — | 1093 |
Long Context Not comparable
DeepSeek Coder 6.7B: —, Wizardlm 70b: 33.3 (#263)
| Benchmark | DeepSeek Coder 6.7B | Wizardlm 70b |
|---|---|---|
| LMArena Longer Query | — | 1097 |
Writing & Preference Not comparable
DeepSeek Coder 6.7B: —, Wizardlm 70b: 34.8 (#269)
| Benchmark | DeepSeek Coder 6.7B | Wizardlm 70b |
|---|---|---|
| LMArena Text | — | 1120 |
| LMArena Creative Writing | — | 1149 |
| LMArena Multi-Turn | — | 1108 |
Frequently asked questions
Is DeepSeek Coder 6.7B better than Wizardlm 70b?
Wizardlm 70b has enough public results to be ranked (#249); DeepSeek Coder 6.7B does not yet, so treat this comparison as directional.
Is DeepSeek Coder 6.7B or Wizardlm 70b better for coding?
DeepSeek Coder 6.7B scores higher on coding benchmarks: 35.8 versus 31.4 in the Noometry coding category.
How many benchmarks do DeepSeek Coder 6.7B and Wizardlm 70b share?
0 benchmarks have published results for both models. DeepSeek Coder 6.7B has 9 scored results on Noometry and Wizardlm 70b has 12.