Model comparison
Qwen1.5-7B vs Wizardlm 70b
Wizardlm 70b is the stronger model overall, scoring 32.4 to 30.8 on the Noometry Index.
Last verified . 11 shared benchmarks.
Alibaba (Qwen)
MicrosoftSummary
- They share 11 benchmarks with published results for both. Qwen1.5-7B scores higher in 1 category and Wizardlm 70b in 6 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Wizardlm 70b leads 34.9 to 29.8.
Side by side
| Qwen1.5-7B | Wizardlm 70b | |
|---|---|---|
| Provider | Alibaba (Qwen) | Microsoft |
| Noometry Index | 30.8 | 32.4 |
| Released | 2024-02-04 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 13 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Qwen1.5-7B: 31.6 (#271), Wizardlm 70b: 30.9 (#280)
| Benchmark | Qwen1.5-7B | Wizardlm 70b |
|---|---|---|
| LMArena Coding | 1107 | 1081 |
Reasoning Too close to call
Qwen1.5-7B: 19.5 (#237), Wizardlm 70b: 19.8 (#231)
| Benchmark | Qwen1.5-7B | Wizardlm 70b |
|---|---|---|
| LMArena Hard Prompts | 1066 | 1079 |
Math Too close to call
Qwen1.5-7B: 29.0 (#222), Wizardlm 70b: 29.7 (#216)
| Benchmark | Qwen1.5-7B | Wizardlm 70b |
|---|---|---|
| LMArena Math | 1080 | 1116 |
Knowledge Not comparable
Qwen1.5-7B: 28.2 (#239), Wizardlm 70b: —
| Benchmark | Qwen1.5-7B | Wizardlm 70b |
|---|---|---|
| LMArena Expert | 1055 | — |
| MMLU | 62.6% | — |
Multilingual Wizardlm 70b leads
Qwen1.5-7B: 28.6 (#266), Wizardlm 70b: 29.8 (#260)
| Benchmark | Qwen1.5-7B | Wizardlm 70b |
|---|---|---|
| LMArena Non-English | 1058 | 1078 |
| LMArena Chinese | 1140 | 1052 |
| LMArena Russian | 1006 | 1155 |
| LMArena German | — | 1083 |
Instruction Following Wizardlm 70b leads
Qwen1.5-7B: 54.4 (#276), Wizardlm 70b: 56.5 (#268)
| Benchmark | Qwen1.5-7B | Wizardlm 70b |
|---|---|---|
| LMArena Instruction Following | 1058 | 1093 |
Long Context Too close to call
Qwen1.5-7B: 33.1 (#261), Wizardlm 70b: 33.3 (#258)
| Benchmark | Qwen1.5-7B | Wizardlm 70b |
|---|---|---|
| LMArena Longer Query | 1090 | 1097 |
Writing & Preference Wizardlm 70b leads
Qwen1.5-7B: 29.8 (#288), Wizardlm 70b: 34.9 (#264)
| Benchmark | Qwen1.5-7B | Wizardlm 70b |
|---|---|---|
| LMArena Text | 1084 | 1120 |
| LMArena Creative Writing | 1035 | 1149 |
| LMArena Multi-Turn | 1061 | 1108 |
Frequently asked questions
Is Qwen1.5-7B better than Wizardlm 70b?
Wizardlm 70b is the stronger model overall, scoring 32.4 to 30.8 on the Noometry Index.
Is Qwen1.5-7B or Wizardlm 70b better for coding?
They score almost the same on coding (31.6 vs 30.9); test both on your own repository before choosing.
How many benchmarks do Qwen1.5-7B and Wizardlm 70b share?
11 benchmarks have published results for both models. Qwen1.5-7B has 13 scored results on Noometry and Wizardlm 70b has 12.