Model comparison
Llama 3-8B vs Wizardlm 70b
Wizardlm 70b is the stronger model overall, scoring 33.0 to 25.5 on the Noometry Index.
Last verified . 12 shared benchmarks.
Meta
MicrosoftSummary
- They share 12 benchmarks with published results for both. Llama 3-8B scores higher in 4 categories and Wizardlm 70b in 3 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where Wizardlm 70b leads 32.2 to 8.8.
Side by side
| Llama 3-8B | Wizardlm 70b | |
|---|---|---|
| Provider | Meta | Microsoft |
| Noometry Index | 25.5 | 33.0 |
| Released | 2024-04-18 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 34 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Llama 3-8B: 31.0 (#289), Wizardlm 70b: 31.4 (#285)
| Benchmark | Llama 3-8B | Wizardlm 70b |
|---|---|---|
| LMArena Coding | 1152 | 1081 |
| BigCodeBench Instruct | 31.9% | — |
| BigCodeBench Complete | 36.9% | — |
| HumanEval+ | 56.7% | — |
| MBPP+ | 54.8% | — |
Reasoning Wizardlm 70b leads
Llama 3-8B: 14.3 (#326), Wizardlm 70b: 20.7 (#234)
| Benchmark | Llama 3-8B | Wizardlm 70b |
|---|---|---|
| LMArena Hard Prompts | 1133 | 1079 |
| Chess Puzzles | 0% | — |
| DTBench | 43.9% | — |
| Adversarial NLI | 57.3% | — |
| Epoch Capabilities Index | 116.45 | — |
| ForecastBench | 58.6 | — |
| WinoGrande | 75.7% | — |
Math Wizardlm 70b leads
Llama 3-8B: 8.8 (#323), Wizardlm 70b: 32.2 (#218)
| Benchmark | Llama 3-8B | Wizardlm 70b |
|---|---|---|
| LMArena Math | 1151 | 1116 |
| OTIS Mock AIME 2024-2025 | 1.9% | — |
| MATH Level 5 | 6.1% | — |
Knowledge Not comparable
Llama 3-8B: 7.8 (#308), Wizardlm 70b: —
| Benchmark | Llama 3-8B | Wizardlm 70b |
|---|---|---|
| GPQA Diamond | 26.1% | — |
| LMArena Expert | 1113 | — |
| ARC (AI2) Challenge | 82.8% | — |
| MMLU | 68.8% | — |
| OpenBookQA | 82.6% | — |
| TriviaQA | 67.7% | — |
Multilingual Llama 3-8B leads
Llama 3-8B: 30.8 (#261), Wizardlm 70b: 29.6 (#265)
| Benchmark | Llama 3-8B | Wizardlm 70b |
|---|---|---|
| LMArena Non-English | 1098 | 1078 |
| LMArena Chinese | 1076 | 1052 |
| LMArena German | 1104 | 1083 |
| LMArena Russian | 1109 | 1155 |
| LMArena French | 1159 | — |
| LMArena Japanese | 967 | — |
| LMArena Korean | 1004 | — |
| LMArena Spanish | 1173 | — |
Instruction Following Llama 3-8B leads
Llama 3-8B: 58.4 (#260), Wizardlm 70b: 56.3 (#273)
| Benchmark | Llama 3-8B | Wizardlm 70b |
|---|---|---|
| LMArena Instruction Following | 1127 | 1093 |
Long Context Too close to call
Llama 3-8B: 34.2 (#251), Wizardlm 70b: 33.3 (#263)
| Benchmark | Llama 3-8B | Wizardlm 70b |
|---|---|---|
| LMArena Longer Query | 1128 | 1097 |
Writing & Preference Llama 3-8B leads
Llama 3-8B: 37.5 (#256), Wizardlm 70b: 34.8 (#269)
| Benchmark | Llama 3-8B | Wizardlm 70b |
|---|---|---|
| LMArena Text | 1166 | 1120 |
| LMArena Creative Writing | 1150 | 1149 |
| LMArena Multi-Turn | 1152 | 1108 |
Frequently asked questions
Is Llama 3-8B better than Wizardlm 70b?
Wizardlm 70b is the stronger model overall, scoring 33.0 to 25.5 on the Noometry Index.
Is Llama 3-8B or Wizardlm 70b better for coding?
They score almost the same on coding (31.0 vs 31.4); test both on your own repository before choosing.
How many benchmarks do Llama 3-8B and Wizardlm 70b share?
12 benchmarks have published results for both models. Llama 3-8B has 34 scored results on Noometry and Wizardlm 70b has 12.