Model comparison
Llama 13b vs Wizardlm 70b
Wizardlm 70b is the stronger model overall, scoring 33.0 to 24.4 on the Noometry Index.
Last verified . 8 shared benchmarks.
Meta
MicrosoftSummary
- They share 8 benchmarks with published results for both. Llama 13b scores higher in 0 categories and Wizardlm 70b in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Wizardlm 70b leads 34.8 to 13.8.
Side by side
| Llama 13b | Wizardlm 70b | |
|---|---|---|
| Provider | Meta | Microsoft |
| Noometry Index | 24.4 | 33.0 |
| Released | 2023-02-24 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 21 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Wizardlm 70b leads
Llama 13b: 21.4 (#337), Wizardlm 70b: 31.4 (#285)
| Benchmark | Llama 13b | Wizardlm 70b |
|---|---|---|
| LMArena Coding | 683 | 1081 |
Reasoning Wizardlm 70b leads
Llama 13b: 14.0 (#329), Wizardlm 70b: 20.7 (#234)
| Benchmark | Llama 13b | Wizardlm 70b |
|---|---|---|
| LMArena Hard Prompts | 728 | 1079 |
| BIG-Bench Hard | 37.9% | — |
| Epoch Capabilities Index | 100.58 | — |
| HellaSwag | 79.2% | — |
| LAMBADA | 75.2% | — |
| PIQA | 80.1% | — |
| WinoGrande | 73% | — |
Math Wizardlm 70b leads
Llama 13b: 26.7 (#256), Wizardlm 70b: 32.2 (#218)
| Benchmark | Llama 13b | Wizardlm 70b |
|---|---|---|
| LMArena Math | 838 | 1116 |
| GSM8K | 20.6% | — |
Knowledge Not comparable
Llama 13b: —, Wizardlm 70b: —
| Benchmark | Llama 13b | Wizardlm 70b |
|---|---|---|
| ARC (AI2) Challenge | 52.7% | — |
| BoolQ | 78.7% | — |
| MMLU | 47.7% | — |
| OpenBookQA | 56.4% | — |
| TriviaQA | 77.9% | — |
Multimodal Not comparable
Llama 13b: —, Wizardlm 70b: —
| Benchmark | Llama 13b | Wizardlm 70b |
|---|---|---|
| ScienceQA | 43.3% | — |
Multilingual Wizardlm 70b leads
Llama 13b: 16.6 (#297), Wizardlm 70b: 29.6 (#265)
| Benchmark | Llama 13b | Wizardlm 70b |
|---|---|---|
| LMArena Non-English | 819 | 1078 |
| LMArena Chinese | — | 1052 |
| LMArena German | — | 1083 |
| LMArena Russian | — | 1155 |
Instruction Following Wizardlm 70b leads
Llama 13b: 36.7 (#305), Wizardlm 70b: 56.3 (#273)
| Benchmark | Llama 13b | Wizardlm 70b |
|---|---|---|
| LMArena Instruction Following | 781 | 1093 |
Long Context Not comparable
Llama 13b: —, Wizardlm 70b: 33.3 (#263)
| Benchmark | Llama 13b | Wizardlm 70b |
|---|---|---|
| LMArena Longer Query | — | 1097 |
Writing & Preference Wizardlm 70b leads
Llama 13b: 13.8 (#312), Wizardlm 70b: 34.8 (#269)
| Benchmark | Llama 13b | Wizardlm 70b |
|---|---|---|
| LMArena Text | 834 | 1120 |
| LMArena Creative Writing | 794 | 1149 |
| LMArena Multi-Turn | 753 | 1108 |
Frequently asked questions
Is Llama 13b better than Wizardlm 70b?
Wizardlm 70b is the stronger model overall, scoring 33.0 to 24.4 on the Noometry Index.
Is Llama 13b or Wizardlm 70b better for coding?
Wizardlm 70b scores higher on coding benchmarks: 31.4 versus 21.4 in the Noometry coding category.
How many benchmarks do Llama 13b and Wizardlm 70b share?
8 benchmarks have published results for both models. Llama 13b has 21 scored results on Noometry and Wizardlm 70b has 12.