Model comparison
DeepSeek-V2 (MoE-236B, May 2024) vs Wizardlm 13b
Wizardlm 13b has enough public results to be ranked (#274); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
DeepSeek
MicrosoftSummary
- The widest gap is in coding, where DeepSeek-V2 (MoE-236B, May 2024) leads 40.4 to 30.1.
Side by side
| DeepSeek-V2 (MoE-236B, May 2024) | Wizardlm 13b | |
|---|---|---|
| Provider | DeepSeek | Microsoft |
| Noometry Index | 40.3 | 31.4 |
| Released | 2024-05-07 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 10 | 10 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V2 (MoE-236B, May 2024) leads
DeepSeek-V2 (MoE-236B, May 2024): 40.4 (#139), Wizardlm 13b: 30.1 (#298)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Wizardlm 13b |
|---|---|---|
| BigCodeBench Instruct | 48.9% | — |
| LMArena Coding | — | 1035 |
| BigCodeBench Complete | 59.4% | — |
Reasoning Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Wizardlm 13b: 19.4 (#259)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Wizardlm 13b |
|---|---|---|
| LMArena Hard Prompts | — | 1018 |
| BIG-Bench Hard | 78.8% | — |
| Epoch Capabilities Index | 124.77 | — |
| HellaSwag | 87.1% | — |
| PIQA | 83.9% | — |
| WinoGrande | 86.3% | — |
Math Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Wizardlm 13b: 30.2 (#238)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Wizardlm 13b |
|---|---|---|
| LMArena Math | — | 1017 |
Knowledge Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Wizardlm 13b: —
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Wizardlm 13b |
|---|---|---|
| ARC (AI2) Challenge | 92.2% | — |
| MMLU | 78.4% | — |
| TriviaQA | 80% | — |
Multilingual Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Wizardlm 13b: 27.1 (#277)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Wizardlm 13b |
|---|---|---|
| LMArena Non-English | — | 1034 |
| LMArena Chinese | — | 1023 |
Instruction Following Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Wizardlm 13b: 53.5 (#285)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Wizardlm 13b |
|---|---|---|
| LMArena Instruction Following | — | 1048 |
Long Context Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Wizardlm 13b: 32.0 (#273)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Wizardlm 13b |
|---|---|---|
| LMArena Longer Query | — | 1054 |
Writing & Preference Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Wizardlm 13b: 30.5 (#287)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Wizardlm 13b |
|---|---|---|
| LMArena Text | — | 1077 |
| LMArena Creative Writing | — | 1091 |
| LMArena Multi-Turn | — | 1047 |
Frequently asked questions
Is DeepSeek-V2 (MoE-236B, May 2024) better than Wizardlm 13b?
Wizardlm 13b has enough public results to be ranked (#274); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
Is DeepSeek-V2 (MoE-236B, May 2024) or Wizardlm 13b better for coding?
DeepSeek-V2 (MoE-236B, May 2024) scores higher on coding benchmarks: 40.4 versus 30.1 in the Noometry coding category.
How many benchmarks do DeepSeek-V2 (MoE-236B, May 2024) and Wizardlm 13b share?
0 benchmarks have published results for both models. DeepSeek-V2 (MoE-236B, May 2024) has 10 scored results on Noometry and Wizardlm 13b has 10.