Model comparison
Qwen2-72B vs Wizardlm 70b
Wizardlm 70b is the stronger model overall, scoring 33.0 to 30.0 on the Noometry Index.
Last verified . 12 shared benchmarks.
Alibaba (Qwen)
MicrosoftSummary
- They share 12 benchmarks with published results for both. Qwen2-72B scores higher in 5 categories and Wizardlm 70b in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Qwen2-72B leads 35.9 to 29.6.
Side by side
| Qwen2-72B | Wizardlm 70b | |
|---|---|---|
| Provider | Alibaba (Qwen) | Microsoft |
| Noometry Index | 30.0 | 33.0 |
| Released | 2024-06-07 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 26 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Wizardlm 70b leads
Qwen2-72B: 29.1 (#310), Wizardlm 70b: 31.4 (#285)
| Benchmark | Qwen2-72B | Wizardlm 70b |
|---|---|---|
| LMArena Coding | 1196 | 1081 |
| WeirdML | 11.3% | — |
| BigCodeBench Instruct | 38.5% | — |
| BigCodeBench Complete | 54% | — |
Agentic & Tool Use Not comparable
Qwen2-72B: 17.0 (#146), Wizardlm 70b: —
| Benchmark | Qwen2-72B | Wizardlm 70b |
|---|---|---|
| TheAgentCompany | 1.1% | — |
| METR Time Horizons | 29.9% | — |
Reasoning Qwen2-72B leads
Qwen2-72B: 23.2 (#181), Wizardlm 70b: 20.7 (#234)
| Benchmark | Qwen2-72B | Wizardlm 70b |
|---|---|---|
| LMArena Hard Prompts | 1191 | 1079 |
| Epoch Capabilities Index | 125.28 | — |
Math Wizardlm 70b leads
Qwen2-72B: 30.2 (#236), Wizardlm 70b: 32.2 (#218)
| Benchmark | Qwen2-72B | Wizardlm 70b |
|---|---|---|
| LMArena Math | 1235 | 1116 |
| MATH Level 5 | 39.1% | — |
Knowledge Not comparable
Qwen2-72B: 21.2 (#275), Wizardlm 70b: —
| Benchmark | Qwen2-72B | Wizardlm 70b |
|---|---|---|
| GPQA Diamond | 40.8% | — |
| LMArena Expert | 1171 | — |
| MMLU | 82.4% | — |
Multilingual Qwen2-72B leads
Qwen2-72B: 35.9 (#244), Wizardlm 70b: 29.6 (#265)
| Benchmark | Qwen2-72B | Wizardlm 70b |
|---|---|---|
| LMArena Non-English | 1176 | 1078 |
| LMArena Chinese | 1240 | 1052 |
| LMArena German | 1151 | 1083 |
| LMArena Russian | 1169 | 1155 |
| LMArena French | 1170 | — |
| LMArena Japanese | 1111 | — |
| LMArena Korean | 1083 | — |
| LMArena Spanish | 1169 | — |
Instruction Following Qwen2-72B leads
Qwen2-72B: 61.7 (#241), Wizardlm 70b: 56.3 (#273)
| Benchmark | Qwen2-72B | Wizardlm 70b |
|---|---|---|
| LMArena Instruction Following | 1181 | 1093 |
Long Context Qwen2-72B leads
Qwen2-72B: 36.1 (#235), Wizardlm 70b: 33.3 (#263)
| Benchmark | Qwen2-72B | Wizardlm 70b |
|---|---|---|
| LMArena Longer Query | 1192 | 1097 |
Writing & Preference Qwen2-72B leads
Qwen2-72B: 40.8 (#241), Wizardlm 70b: 34.8 (#269)
| Benchmark | Qwen2-72B | Wizardlm 70b |
|---|---|---|
| LMArena Text | 1203 | 1120 |
| LMArena Creative Writing | 1181 | 1149 |
| LMArena Multi-Turn | 1196 | 1108 |
Frequently asked questions
Is Qwen2-72B better than Wizardlm 70b?
Wizardlm 70b is the stronger model overall, scoring 33.0 to 30.0 on the Noometry Index.
Is Qwen2-72B or Wizardlm 70b better for coding?
Wizardlm 70b scores higher on coding benchmarks: 31.4 versus 29.1 in the Noometry coding category.
How many benchmarks do Qwen2-72B and Wizardlm 70b share?
12 benchmarks have published results for both models. Qwen2-72B has 26 scored results on Noometry and Wizardlm 70b has 12.