Model comparison
Qwen1.5-72B vs Wizardlm 70b
Wizardlm 70b is the stronger model overall, scoring 33.0 to 30.8 on the Noometry Index.
Last verified . 12 shared benchmarks.
Alibaba (Qwen)
MicrosoftSummary
- They share 12 benchmarks with published results for both. Qwen1.5-72B scores higher in 7 categories and Wizardlm 70b in 0 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Qwen1.5-72B leads 33.2 to 29.6.
Side by side
| Qwen1.5-72B | Wizardlm 70b | |
|---|---|---|
| Provider | Alibaba (Qwen) | Microsoft |
| Noometry Index | 30.8 | 33.0 |
| Released | 2024-02-04 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 22 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Qwen1.5-72B: 31.9 (#277), Wizardlm 70b: 31.4 (#285)
| Benchmark | Qwen1.5-72B | Wizardlm 70b |
|---|---|---|
| LMArena Coding | 1165 | 1081 |
| BigCodeBench Instruct | 33.2% | — |
| BigCodeBench Complete | 40.3% | — |
| HumanEval+ | 59.1% | — |
| MBPP+ | 61.6% | — |
Reasoning Qwen1.5-72B leads
Qwen1.5-72B: 22.2 (#203), Wizardlm 70b: 20.7 (#234)
| Benchmark | Qwen1.5-72B | Wizardlm 70b |
|---|---|---|
| LMArena Hard Prompts | 1148 | 1079 |
Math Qwen1.5-72B leads
Qwen1.5-72B: 33.2 (#205), Wizardlm 70b: 32.2 (#218)
| Benchmark | Qwen1.5-72B | Wizardlm 70b |
|---|---|---|
| LMArena Math | 1164 | 1116 |
Knowledge Not comparable
Qwen1.5-72B: 11.5 (#300), Wizardlm 70b: —
| Benchmark | Qwen1.5-72B | Wizardlm 70b |
|---|---|---|
| GPQA Diamond | 28.8% | — |
| LMArena Expert | 1136 | — |
Multilingual Qwen1.5-72B leads
Qwen1.5-72B: 33.2 (#253), Wizardlm 70b: 29.6 (#265)
| Benchmark | Qwen1.5-72B | Wizardlm 70b |
|---|---|---|
| LMArena Non-English | 1135 | 1078 |
| LMArena Chinese | 1186 | 1052 |
| LMArena German | 1084 | 1083 |
| LMArena Russian | 1104 | 1155 |
| LMArena French | 1159 | — |
| LMArena Japanese | 1061 | — |
| LMArena Korean | 1050 | — |
| LMArena Spanish | 1110 | — |
Instruction Following Qwen1.5-72B leads
Qwen1.5-72B: 59.3 (#256), Wizardlm 70b: 56.3 (#273)
| Benchmark | Qwen1.5-72B | Wizardlm 70b |
|---|---|---|
| LMArena Instruction Following | 1141 | 1093 |
Long Context Qwen1.5-72B leads
Qwen1.5-72B: 35.1 (#243), Wizardlm 70b: 33.3 (#263)
| Benchmark | Qwen1.5-72B | Wizardlm 70b |
|---|---|---|
| LMArena Longer Query | 1157 | 1097 |
Writing & Preference Qwen1.5-72B leads
Qwen1.5-72B: 37.3 (#258), Wizardlm 70b: 34.8 (#269)
| Benchmark | Qwen1.5-72B | Wizardlm 70b |
|---|---|---|
| LMArena Text | 1166 | 1120 |
| LMArena Creative Writing | 1137 | 1149 |
| LMArena Multi-Turn | 1160 | 1108 |
Frequently asked questions
Is Qwen1.5-72B better than Wizardlm 70b?
Wizardlm 70b is the stronger model overall, scoring 33.0 to 30.8 on the Noometry Index.
Is Qwen1.5-72B or Wizardlm 70b better for coding?
They score almost the same on coding (31.9 vs 31.4); test both on your own repository before choosing.
How many benchmarks do Qwen1.5-72B and Wizardlm 70b share?
12 benchmarks have published results for both models. Qwen1.5-72B has 22 scored results on Noometry and Wizardlm 70b has 12.