Model comparison
Llama 3.1-405B vs Wizardlm 13b
Llama 3.1-405B and Wizardlm 13b score almost the same on the Noometry Index (30.7 vs 31.4), so choose on price, context window or the category you care about most.
Last verified . 10 shared benchmarks.
Meta
MicrosoftSummary
- They share 10 benchmarks with published results for both. Llama 3.1-405B scores higher in 5 categories and Wizardlm 13b in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Llama 3.1-405B leads 40.7 to 27.1.
Side by side
| Llama 3.1-405B | Wizardlm 13b | |
|---|---|---|
| Provider | Meta | Microsoft |
| Noometry Index | 30.7 | 31.4 |
| Released | 2024-07-23 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 42 | 10 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 3.1-405B leads
Llama 3.1-405B: 33.1 (#262), Wizardlm 13b: 30.1 (#298)
| Benchmark | Llama 3.1-405B | Wizardlm 13b |
|---|---|---|
| LMArena Coding | 1291 | 1035 |
| WeirdML | 21.4% | — |
Agentic & Tool Use Not comparable
Llama 3.1-405B: 21.0 (#140), Wizardlm 13b: —
| Benchmark | Llama 3.1-405B | Wizardlm 13b |
|---|---|---|
| TheAgentCompany | 7.4% | — |
| Cybench | 7.5% | — |
Reasoning Wizardlm 13b leads
Llama 3.1-405B: 16.8 (#300), Wizardlm 13b: 19.4 (#259)
| Benchmark | Llama 3.1-405B | Wizardlm 13b |
|---|---|---|
| LMArena Hard Prompts | 1269 | 1018 |
| SimpleBench | 23% | — |
| Kagi LLM Benchmark | 45% | — |
| DTBench | 61.4% | — |
| BIG-Bench Hard | 82.9% | — |
| Epoch Capabilities Index | 128.75 | — |
| ForecastBench | 59.9 | — |
| HellaSwag | 89.2% | — |
| PIQA | 85.9% | — |
| WinoGrande | 89.2% | — |
Math Wizardlm 13b leads
Llama 3.1-405B: 18.4 (#290), Wizardlm 13b: 30.2 (#238)
| Benchmark | Llama 3.1-405B | Wizardlm 13b |
|---|---|---|
| LMArena Math | 1281 | 1017 |
| OTIS Mock AIME 2024-2025 | 9.7% | — |
| Omni-MATH | 24.9% | — |
| MATH Level 5 | 49.8% | — |
Knowledge Not comparable
Llama 3.1-405B: 30.4 (#227), Wizardlm 13b: —
| Benchmark | Llama 3.1-405B | Wizardlm 13b |
|---|---|---|
| GPQA Diamond | 50.9% | — |
| MMLU-Pro | 72.3% | — |
| Confabulations | 17.6% | — |
| GPQA (HELM) | 52.2% | — |
| LMArena Expert | 1243 | — |
| ARC (AI2) Challenge | 95.3% | — |
| MMLU | 84.5% | — |
| TriviaQA | 82.7% | — |
Multilingual Llama 3.1-405B leads
Llama 3.1-405B: 40.7 (#214), Wizardlm 13b: 27.1 (#277)
| Benchmark | Llama 3.1-405B | Wizardlm 13b |
|---|---|---|
| LMArena Non-English | 1248 | 1034 |
| LMArena Chinese | 1242 | 1023 |
| LMArena French | 1279 | — |
| LMArena German | 1252 | — |
| LMArena Japanese | 1208 | — |
| LMArena Korean | 1184 | — |
| LMArena Russian | 1265 | — |
| LMArena Spanish | 1260 | — |
Instruction Following Llama 3.1-405B leads
Llama 3.1-405B: 65.9 (#214), Wizardlm 13b: 53.5 (#285)
| Benchmark | Llama 3.1-405B | Wizardlm 13b |
|---|---|---|
| LMArena Instruction Following | 1259 | 1048 |
| IFEval | 81.1% | — |
Long Context Llama 3.1-405B leads
Llama 3.1-405B: 38.4 (#197), Wizardlm 13b: 32.0 (#273)
| Benchmark | Llama 3.1-405B | Wizardlm 13b |
|---|---|---|
| LMArena Longer Query | 1266 | 1054 |
Writing & Preference Llama 3.1-405B leads
Llama 3.1-405B: 38.9 (#251), Wizardlm 13b: 30.5 (#287)
| Benchmark | Llama 3.1-405B | Wizardlm 13b |
|---|---|---|
| LMArena Text | 1284 | 1077 |
| LMArena Creative Writing | 1262 | 1091 |
| LMArena Multi-Turn | 1297 | 1047 |
| EQ-Bench Creative Writing | 870 | — |
| WildBench | 78.3% | — |
Frequently asked questions
Is Llama 3.1-405B better than Wizardlm 13b?
Llama 3.1-405B and Wizardlm 13b score almost the same on the Noometry Index (30.7 vs 31.4), so choose on price, context window or the category you care about most.
Is Llama 3.1-405B or Wizardlm 13b better for coding?
Llama 3.1-405B scores higher on coding benchmarks: 33.1 versus 30.1 in the Noometry coding category.
How many benchmarks do Llama 3.1-405B and Wizardlm 13b share?
10 benchmarks have published results for both models. Llama 3.1-405B has 42 scored results on Noometry and Wizardlm 13b has 10.