Model comparison
Qwen-14B vs Wizardlm 70b
Wizardlm 70b is the stronger model overall, scoring 33.0 to 31.4 on the Noometry Index.
Last verified . 10 shared benchmarks.
Alibaba (Qwen)
MicrosoftSummary
- They share 10 benchmarks with published results for both. Qwen-14B scores higher in 0 categories and Wizardlm 70b in 7 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Wizardlm 70b leads 34.8 to 27.6.
Side by side
| Qwen-14B | Wizardlm 70b | |
|---|---|---|
| Provider | Alibaba (Qwen) | Microsoft |
| Noometry Index | 31.4 | 33.0 |
| Released | 2023-09-24 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 18 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Qwen-14B: 31.2 (#288), Wizardlm 70b: 31.4 (#285)
| Benchmark | Qwen-14B | Wizardlm 70b |
|---|---|---|
| LMArena Coding | 1071 | 1081 |
Reasoning Wizardlm 70b leads
Qwen-14B: 19.6 (#257), Wizardlm 70b: 20.7 (#234)
| Benchmark | Qwen-14B | Wizardlm 70b |
|---|---|---|
| LMArena Hard Prompts | 1027 | 1079 |
| BIG-Bench Hard | 55% | — |
| Epoch Capabilities Index | 113.03 | — |
| LAMBADA | 71.1% | — |
| PIQA | 79.9% | — |
Math Wizardlm 70b leads
Qwen-14B: 31.2 (#227), Wizardlm 70b: 32.2 (#218)
| Benchmark | Qwen-14B | Wizardlm 70b |
|---|---|---|
| LMArena Math | 1068 | 1116 |
| GSM8K | 61.3% | — |
Knowledge Not comparable
Qwen-14B: —, Wizardlm 70b: —
| Benchmark | Qwen-14B | Wizardlm 70b |
|---|---|---|
| ARC (AI2) Challenge | 84.4% | — |
| BoolQ | 86.2% | — |
| MMLU | 66.3% | — |
Multilingual Wizardlm 70b leads
Qwen-14B: 27.5 (#275), Wizardlm 70b: 29.6 (#265)
| Benchmark | Qwen-14B | Wizardlm 70b |
|---|---|---|
| LMArena Non-English | 1041 | 1078 |
| LMArena Chinese | 1077 | 1052 |
| LMArena German | — | 1083 |
| LMArena Russian | — | 1155 |
Instruction Following Wizardlm 70b leads
Qwen-14B: 52.4 (#289), Wizardlm 70b: 56.3 (#273)
| Benchmark | Qwen-14B | Wizardlm 70b |
|---|---|---|
| LMArena Instruction Following | 1031 | 1093 |
Long Context Wizardlm 70b leads
Qwen-14B: 31.3 (#280), Wizardlm 70b: 33.3 (#263)
| Benchmark | Qwen-14B | Wizardlm 70b |
|---|---|---|
| LMArena Longer Query | 1028 | 1097 |
Writing & Preference Wizardlm 70b leads
Qwen-14B: 27.6 (#299), Wizardlm 70b: 34.8 (#269)
| Benchmark | Qwen-14B | Wizardlm 70b |
|---|---|---|
| LMArena Text | 1051 | 1120 |
| LMArena Creative Writing | 1028 | 1149 |
| LMArena Multi-Turn | 1022 | 1108 |
Frequently asked questions
Is Qwen-14B better than Wizardlm 70b?
Wizardlm 70b is the stronger model overall, scoring 33.0 to 31.4 on the Noometry Index.
Is Qwen-14B or Wizardlm 70b better for coding?
They score almost the same on coding (31.2 vs 31.4); test both on your own repository before choosing.
How many benchmarks do Qwen-14B and Wizardlm 70b share?
10 benchmarks have published results for both models. Qwen-14B has 18 scored results on Noometry and Wizardlm 70b has 12.