Model comparison
Qwen2.5 72B Instruct vs Wizardlm 70b
Qwen2.5 72B Instruct and Wizardlm 70b score almost the same on the Noometry Index (31.5 vs 32.4), so choose on price, context window or the category you care about most.
Last verified . 12 shared benchmarks.
Alibaba (Qwen)
MicrosoftSummary
- They share 12 benchmarks with published results for both. Qwen2.5 72B Instruct scores higher in 6 categories and Wizardlm 70b in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen2.5 72B Instruct leads 46.9 to 34.9.
Side by side
| Qwen2.5 72B Instruct | Wizardlm 70b | |
|---|---|---|
| Provider | Alibaba (Qwen) | Microsoft |
| Noometry Index | 31.5 | 32.4 |
| Released | 2024-09 | — |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 8K | — |
| Input $ / M tokens | $1.40 | — |
| Output $ / M tokens | $5.60 | — |
| Results tracked | 43 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5 72B Instruct leads
Qwen2.5 72B Instruct: 32.8 (#256), Wizardlm 70b: 30.9 (#280)
| Benchmark | Qwen2.5 72B Instruct | Wizardlm 70b |
|---|---|---|
| LMArena Coding | 1293 | 1081 |
| WeirdML | 16% | — |
| BigCodeBench Instruct | 45.8% | — |
| BigCodeBench Complete | 55.9% | — |
Agentic & Tool Use Not comparable
Qwen2.5 72B Instruct: 22.0 (#124), Wizardlm 70b: —
| Benchmark | Qwen2.5 72B Instruct | Wizardlm 70b |
|---|---|---|
| TheAgentCompany | 5.7% | — |
| BALROG | 16.2% | — |
| METR Time Horizons | 35.8% | — |
Reasoning Qwen2.5 72B Instruct leads
Qwen2.5 72B Instruct: 21.4 (#197), Wizardlm 70b: 19.8 (#231)
| Benchmark | Qwen2.5 72B Instruct | Wizardlm 70b |
|---|---|---|
| LMArena Hard Prompts | 1271 | 1079 |
| DTBench | 62.9% | — |
| LMCA | 13.4% | — |
| BIG-Bench Hard | 79.8% | — |
| Epoch Capabilities Index | 129.01 | — |
| ForecastBench | 57.5 | — |
| HellaSwag | 84.8% | — |
| PIQA | 82.6% | — |
| WinoGrande | 82.3% | — |
Math Wizardlm 70b leads
Qwen2.5 72B Instruct: 18.1 (#281), Wizardlm 70b: 29.7 (#216)
| Benchmark | Qwen2.5 72B Instruct | Wizardlm 70b |
|---|---|---|
| LMArena Math | 1283 | 1116 |
| OTIS Mock AIME 2024-2025 | 8.1% | — |
| Omni-MATH | 33% | — |
| MATH Level 5 | 63.2% | — |
Knowledge Not comparable
Qwen2.5 72B Instruct: 26.9 (#247), Wizardlm 70b: —
| Benchmark | Qwen2.5 72B Instruct | Wizardlm 70b |
|---|---|---|
| GPQA Diamond | 49.1% | — |
| MMLU-Pro | 63.1% | — |
| Confabulations | 19.1% | — |
| GPQA (HELM) | 42.6% | — |
| LMArena Expert | 1245 | — |
| ARC (AI2) Challenge | 94.5% | — |
| MMLU | 85.3% | — |
| TriviaQA | 71.9% | — |
Multilingual Qwen2.5 72B Instruct leads
Qwen2.5 72B Instruct: 41.2 (#208), Wizardlm 70b: 29.8 (#260)
| Benchmark | Qwen2.5 72B Instruct | Wizardlm 70b |
|---|---|---|
| LMArena Non-English | 1252 | 1078 |
| LMArena Chinese | 1272 | 1052 |
| LMArena German | 1234 | 1083 |
| LMArena Russian | 1264 | 1155 |
| LMArena French | 1279 | — |
| LMArena Japanese | 1180 | — |
| LMArena Korean | 1188 | — |
| LMArena Spanish | 1255 | — |
Instruction Following Qwen2.5 72B Instruct leads
Qwen2.5 72B Instruct: 65.7 (#216), Wizardlm 70b: 56.5 (#268)
| Benchmark | Qwen2.5 72B Instruct | Wizardlm 70b |
|---|---|---|
| LMArena Instruction Following | 1254 | 1093 |
| IFEval | 80.6% | — |
Long Context Qwen2.5 72B Instruct leads
Qwen2.5 72B Instruct: 38.9 (#183), Wizardlm 70b: 33.3 (#258)
| Benchmark | Qwen2.5 72B Instruct | Wizardlm 70b |
|---|---|---|
| LMArena Longer Query | 1282 | 1097 |
Writing & Preference Qwen2.5 72B Instruct leads
Qwen2.5 72B Instruct: 46.9 (#210), Wizardlm 70b: 34.9 (#264)
| Benchmark | Qwen2.5 72B Instruct | Wizardlm 70b |
|---|---|---|
| LMArena Text | 1269 | 1120 |
| LMArena Creative Writing | 1221 | 1149 |
| LMArena Multi-Turn | 1272 | 1108 |
| WildBench | 80.2% | — |
Frequently asked questions
Is Qwen2.5 72B Instruct better than Wizardlm 70b?
Qwen2.5 72B Instruct and Wizardlm 70b score almost the same on the Noometry Index (31.5 vs 32.4), so choose on price, context window or the category you care about most.
Is Qwen2.5 72B Instruct or Wizardlm 70b better for coding?
Qwen2.5 72B Instruct scores higher on coding benchmarks: 32.8 versus 30.9 in the Noometry coding category.
How many benchmarks do Qwen2.5 72B Instruct and Wizardlm 70b share?
12 benchmarks have published results for both models. Qwen2.5 72B Instruct has 43 scored results on Noometry and Wizardlm 70b has 12.