Model comparison
Llama 13b vs Wizardlm 13b
Wizardlm 13b is the stronger model overall, scoring 30.8 to 23.9 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 13b in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Wizardlm 13b leads 30.7 to 13.9.
Side by side
| Llama 13b | Wizardlm 13b | |
|---|---|---|
| Provider | Meta | Microsoft |
| Noometry Index | 23.9 | 30.8 |
| Released | 2023-02-24 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 21 | 10 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Wizardlm 13b leads
Llama 13b: 20.9 (#332), Wizardlm 13b: 29.6 (#293)
| Benchmark | Llama 13b | Wizardlm 13b |
|---|---|---|
| LMArena Coding | 683 | 1035 |
Reasoning Wizardlm 13b leads
Llama 13b: 13.4 (#327), Wizardlm 13b: 18.5 (#265)
| Benchmark | Llama 13b | Wizardlm 13b |
|---|---|---|
| LMArena Hard Prompts | 728 | 1018 |
| BIG-Bench Hard | 37.9% | — |
| Epoch Capabilities Index | 100.09 | — |
| HellaSwag | 79.2% | — |
| LAMBADA | 75.2% | — |
| PIQA | 80.1% | — |
| WinoGrande | 73% | — |
Math Wizardlm 13b leads
Llama 13b: 24.4 (#259), Wizardlm 13b: 27.8 (#235)
| Benchmark | Llama 13b | Wizardlm 13b |
|---|---|---|
| LMArena Math | 838 | 1017 |
| GSM8K | 20.6% | — |
Knowledge Not comparable
Llama 13b: —, Wizardlm 13b: —
| Benchmark | Llama 13b | Wizardlm 13b |
|---|---|---|
| ARC (AI2) Challenge | 52.7% | — |
| BoolQ | 78.7% | — |
| MMLU | 47.7% | — |
| OpenBookQA | 56.4% | — |
| TriviaQA | 77.9% | — |
Multimodal Not comparable
Llama 13b: —, Wizardlm 13b: —
| Benchmark | Llama 13b | Wizardlm 13b |
|---|---|---|
| ScienceQA | 43.3% | — |
Multilingual Wizardlm 13b leads
Llama 13b: 16.8 (#292), Wizardlm 13b: 27.3 (#272)
| Benchmark | Llama 13b | Wizardlm 13b |
|---|---|---|
| LMArena Non-English | 819 | 1034 |
| LMArena Chinese | — | 1023 |
Instruction Following Wizardlm 13b leads
Llama 13b: 36.9 (#300), Wizardlm 13b: 53.7 (#280)
| Benchmark | Llama 13b | Wizardlm 13b |
|---|---|---|
| LMArena Instruction Following | 781 | 1049 |
Long Context Not comparable
Llama 13b: —, Wizardlm 13b: 32.0 (#268)
| Benchmark | Llama 13b | Wizardlm 13b |
|---|---|---|
| LMArena Longer Query | — | 1054 |
Writing & Preference Wizardlm 13b leads
Llama 13b: 13.9 (#307), Wizardlm 13b: 30.7 (#282)
| Benchmark | Llama 13b | Wizardlm 13b |
|---|---|---|
| LMArena Text | 834 | 1077 |
| LMArena Creative Writing | 794 | 1090 |
| LMArena Multi-Turn | 753 | 1047 |
Frequently asked questions
Is Llama 13b better than Wizardlm 13b?
Wizardlm 13b is the stronger model overall, scoring 30.8 to 23.9 on the Noometry Index.
Is Llama 13b or Wizardlm 13b better for coding?
Wizardlm 13b scores higher on coding benchmarks: 29.6 versus 20.9 in the Noometry coding category.
How many benchmarks do Llama 13b and Wizardlm 13b share?
8 benchmarks have published results for both models. Llama 13b has 21 scored results on Noometry and Wizardlm 13b has 10.