Model comparison
Llama 2-7B vs Wizardlm 70b
Wizardlm 70b is the stronger model overall, scoring 32.4 to 28.6 on the Noometry Index.
Last verified . 12 shared benchmarks.
Meta
MicrosoftSummary
- They share 12 benchmarks with published results for both. Llama 2-7B scores higher in 0 categories and Wizardlm 70b in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Wizardlm 70b leads 34.9 to 28.1.
Side by side
| Llama 2-7B | Wizardlm 70b | |
|---|---|---|
| Provider | Meta | Microsoft |
| Noometry Index | 28.6 | 32.4 |
| Released | 2023-07-18 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 29 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Wizardlm 70b leads
Llama 2-7B: 28.7 (#302), Wizardlm 70b: 30.9 (#280)
| Benchmark | Llama 2-7B | Wizardlm 70b |
|---|---|---|
| LMArena Coding | 1002 | 1081 |
Reasoning Wizardlm 70b leads
Llama 2-7B: 15.1 (#309), Wizardlm 70b: 19.8 (#231)
| Benchmark | Llama 2-7B | Wizardlm 70b |
|---|---|---|
| LMArena Hard Prompts | 1009 | 1079 |
| Chess Puzzles | 0% | — |
| BIG-Bench Hard | 39.2% | — |
| Epoch Capabilities Index | 98.54 | — |
| HellaSwag | 77.2% | — |
| LAMBADA | 73.3% | — |
| PIQA | 78.8% | — |
| WinoGrande | 69.2% | — |
Math Wizardlm 70b leads
Llama 2-7B: 28.2 (#231), Wizardlm 70b: 29.7 (#216)
| Benchmark | Llama 2-7B | Wizardlm 70b |
|---|---|---|
| LMArena Math | 1042 | 1116 |
| GSM8K | 16.7% | — |
Knowledge Not comparable
Llama 2-7B: 27.7 (#243), Wizardlm 70b: —
| Benchmark | Llama 2-7B | Wizardlm 70b |
|---|---|---|
| LMArena Expert | 1036 | — |
| ARC (AI2) Challenge | 45.9% | — |
| BoolQ | 77.9% | — |
| MMLU | 45.8% | — |
| OpenBookQA | 58.6% | — |
| TriviaQA | 73.7% | — |
Multimodal Not comparable
Llama 2-7B: —, Wizardlm 70b: —
| Benchmark | Llama 2-7B | Wizardlm 70b |
|---|---|---|
| ScienceQA | 43.1% | — |
Multilingual Wizardlm 70b leads
Llama 2-7B: 23.9 (#288), Wizardlm 70b: 29.8 (#260)
| Benchmark | Llama 2-7B | Wizardlm 70b |
|---|---|---|
| LMArena Non-English | 973 | 1078 |
| LMArena Chinese | 973 | 1052 |
| LMArena German | 978 | 1083 |
| LMArena Russian | 995 | 1155 |
| LMArena French | 969 | — |
| LMArena Spanish | 1007 | — |
Instruction Following Wizardlm 70b leads
Llama 2-7B: 51.0 (#293), Wizardlm 70b: 56.5 (#268)
| Benchmark | Llama 2-7B | Wizardlm 70b |
|---|---|---|
| LMArena Instruction Following | 1006 | 1093 |
Long Context Wizardlm 70b leads
Llama 2-7B: 30.4 (#282), Wizardlm 70b: 33.3 (#258)
| Benchmark | Llama 2-7B | Wizardlm 70b |
|---|---|---|
| LMArena Longer Query | 999 | 1097 |
Writing & Preference Wizardlm 70b leads
Llama 2-7B: 28.1 (#293), Wizardlm 70b: 34.9 (#264)
| Benchmark | Llama 2-7B | Wizardlm 70b |
|---|---|---|
| LMArena Text | 1053 | 1120 |
| LMArena Creative Writing | 1033 | 1149 |
| LMArena Multi-Turn | 1029 | 1108 |
Frequently asked questions
Is Llama 2-7B better than Wizardlm 70b?
Wizardlm 70b is the stronger model overall, scoring 32.4 to 28.6 on the Noometry Index.
Is Llama 2-7B or Wizardlm 70b better for coding?
Wizardlm 70b scores higher on coding benchmarks: 30.9 versus 28.7 in the Noometry coding category.
How many benchmarks do Llama 2-7B and Wizardlm 70b share?
12 benchmarks have published results for both models. Llama 2-7B has 29 scored results on Noometry and Wizardlm 70b has 12.