Model comparison
Llama 2-13B vs Wizardlm 70b
Wizardlm 70b is the stronger model overall, scoring 33.0 to 29.6 on the Noometry Index.
Last verified . 12 shared benchmarks.
Meta
MicrosoftSummary
- They share 12 benchmarks with published results for both. Llama 2-13B scores higher in 0 categories and Wizardlm 70b in 7 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Wizardlm 70b leads 20.7 to 12.8.
Side by side
| Llama 2-13B | Wizardlm 70b | |
|---|---|---|
| Provider | Meta | Microsoft |
| Noometry Index | 29.6 | 33.0 |
| Released | 2023-07-18 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 32 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Llama 2-13B: 30.9 (#291), Wizardlm 70b: 31.4 (#285)
| Benchmark | Llama 2-13B | Wizardlm 70b |
|---|---|---|
| LMArena Coding | 1062 | 1081 |
Reasoning Wizardlm 70b leads
Llama 2-13B: 12.8 (#337), Wizardlm 70b: 20.7 (#234)
| Benchmark | Llama 2-13B | Wizardlm 70b |
|---|---|---|
| LMArena Hard Prompts | 1051 | 1079 |
| Chess Puzzles | 0% | — |
| DTBench | 42.2% | — |
| BIG-Bench Hard | 58.2% | — |
| Epoch Capabilities Index | 106.17 | — |
| HellaSwag | 80.7% | — |
| LAMBADA | 76.5% | — |
| PIQA | 80.8% | — |
| WinoGrande | 72.8% | — |
Math Wizardlm 70b leads
Llama 2-13B: 31.1 (#229), Wizardlm 70b: 32.2 (#218)
| Benchmark | Llama 2-13B | Wizardlm 70b |
|---|---|---|
| LMArena Math | 1065 | 1116 |
| GSM8K | 36.9% | — |
Knowledge Not comparable
Llama 2-13B: 28.1 (#249), Wizardlm 70b: —
| Benchmark | Llama 2-13B | Wizardlm 70b |
|---|---|---|
| LMArena Expert | 1030 | — |
| ARC (AI2) Challenge | 60.3% | — |
| BoolQ | 82.4% | — |
| MMLU | 55.6% | — |
| OpenBookQA | 57% | — |
| TriviaQA | 79.6% | — |
Multimodal Not comparable
Llama 2-13B: —, Wizardlm 70b: —
| Benchmark | Llama 2-13B | Wizardlm 70b |
|---|---|---|
| ScienceQA | 55.8% | — |
Multilingual Wizardlm 70b leads
Llama 2-13B: 26.5 (#279), Wizardlm 70b: 29.6 (#265)
| Benchmark | Llama 2-13B | Wizardlm 70b |
|---|---|---|
| LMArena Non-English | 1024 | 1078 |
| LMArena Chinese | 1001 | 1052 |
| LMArena German | 1009 | 1083 |
| LMArena Russian | 1055 | 1155 |
| LMArena French | 1044 | — |
| LMArena Japanese | 894 | — |
| LMArena Korean | 953 | — |
| LMArena Spanish | 1087 | — |
Instruction Following Wizardlm 70b leads
Llama 2-13B: 53.3 (#287), Wizardlm 70b: 56.3 (#273)
| Benchmark | Llama 2-13B | Wizardlm 70b |
|---|---|---|
| LMArena Instruction Following | 1045 | 1093 |
Long Context Too close to call
Llama 2-13B: 32.3 (#269), Wizardlm 70b: 33.3 (#263)
| Benchmark | Llama 2-13B | Wizardlm 70b |
|---|---|---|
| LMArena Longer Query | 1064 | 1097 |
Writing & Preference Wizardlm 70b leads
Llama 2-13B: 29.8 (#289), Wizardlm 70b: 34.8 (#269)
| Benchmark | Llama 2-13B | Wizardlm 70b |
|---|---|---|
| LMArena Text | 1084 | 1120 |
| LMArena Creative Writing | 1047 | 1149 |
| LMArena Multi-Turn | 1050 | 1108 |
Frequently asked questions
Is Llama 2-13B better than Wizardlm 70b?
Wizardlm 70b is the stronger model overall, scoring 33.0 to 29.6 on the Noometry Index.
Is Llama 2-13B or Wizardlm 70b better for coding?
They score almost the same on coding (30.9 vs 31.4); test both on your own repository before choosing.
How many benchmarks do Llama 2-13B and Wizardlm 70b share?
12 benchmarks have published results for both models. Llama 2-13B has 32 scored results on Noometry and Wizardlm 70b has 12.