Model comparison
Qwen Plus vs Qwen2.5 72B Instruct
Qwen Plus is the stronger model overall, scoring 37.1 to 31.9 on the Noometry Index.
Last verified . 18 shared benchmarks.
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. Qwen Plus scores higher in 8 categories and Qwen2.5 72B Instruct in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen Plus leads 28.4 to 22.3.
- The biggest single-benchmark swing is DTBench: 81.1% for Qwen Plus and 62.9% for Qwen2.5 72B Instruct.
- Qwen Plus is cheaper at $0.40 / $1.20 per million input/output tokens, against $1.40 / $5.60 for Qwen2.5 72B Instruct.
- Qwen Plus accepts more context: 1M tokens versus 131K.
- Qwen2.5 72B Instruct has downloadable open weights; the other is API-only.
Side by side
| Qwen Plus | Qwen2.5 72B Instruct | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 37.1 | 31.9 |
| Released | 2024-01-25 | 2024-09 |
| Weights | Proprietary | Open |
| Context window | 1M | 131K |
| Max output | 33K | 8K |
| Input $ / M tokens | $0.40 | $1.40 |
| Output $ / M tokens | $1.20 | $5.60 |
| Results tracked | 20 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen Plus leads
Qwen Plus: 38.9 (#167), Qwen2.5 72B Instruct: 33.2 (#260)
| Benchmark | Qwen Plus | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Coding | 1328 | 1292 |
| WeirdML | — | 16% |
| BigCodeBench Instruct | — | 45.8% |
| BigCodeBench Complete | — | 55.9% |
Agentic & Tool Use Not comparable
Qwen Plus: —, Qwen2.5 72B Instruct: 22.1 (#133)
| Benchmark | Qwen Plus | Qwen2.5 72B Instruct |
|---|---|---|
| TheAgentCompany | — | 5.7% |
| BALROG | — | 16.2% |
| METR Time Horizons | — | 35.8% |
Reasoning Qwen Plus leads
Qwen Plus: 28.4 (#107), Qwen2.5 72B Instruct: 22.3 (#199)
| Benchmark | Qwen Plus | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1317 | 1271 |
| DTBench | 81.1% | 62.9% |
| LMCA | 24% | 13.4% |
| Kagi LLM Benchmark | 63.3% | — |
| BIG-Bench Hard | — | 79.8% |
| Epoch Capabilities Index | — | 129 |
| ForecastBench | — | 57.5 |
| HellaSwag | — | 84.8% |
| PIQA | — | 82.6% |
| WinoGrande | — | 82.3% |
Math Qwen Plus leads
Qwen Plus: 23.3 (#271), Qwen2.5 72B Instruct: 19.3 (#287)
| Benchmark | Qwen Plus | Qwen2.5 72B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 17.8% | 8.1% |
| LMArena Math | 1326 | 1283 |
| MATH Level 5 | 65.3% | 63.2% |
| Omni-MATH | — | 33% |
| FrontierMath (Feb 2025 set) | 1.7% | — |
Knowledge Too close to call
Qwen Plus: 27.4 (#251), Qwen2.5 72B Instruct: 27.0 (#253)
| Benchmark | Qwen Plus | Qwen2.5 72B Instruct |
|---|---|---|
| GPQA Diamond | 48.1% | 49.1% |
| LMArena Expert | 1328 | 1245 |
| MMLU-Pro | — | 63.1% |
| Confabulations | — | 19.1% |
| GPQA (HELM) | — | 42.6% |
| ARC (AI2) Challenge | — | 94.5% |
| MMLU | — | 85.3% |
| TriviaQA | — | 71.9% |
Multilingual Qwen Plus leads
Qwen Plus: 45.1 (#175), Qwen2.5 72B Instruct: 41.0 (#213)
| Benchmark | Qwen Plus | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Non-English | 1310 | 1252 |
| LMArena Chinese | 1347 | 1272 |
| LMArena Japanese | 1251 | 1180 |
| LMArena Russian | 1323 | 1264 |
| LMArena French | — | 1280 |
| LMArena German | — | 1234 |
| LMArena Korean | — | 1188 |
| LMArena Spanish | — | 1256 |
Instruction Following Qwen Plus leads
Qwen Plus: 68.8 (#181), Qwen2.5 72B Instruct: 65.5 (#221)
| Benchmark | Qwen Plus | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Instruction Following | 1303 | 1254 |
| IFEval | — | 80.6% |
Long Context Qwen Plus leads
Qwen Plus: 40.3 (#158), Qwen2.5 72B Instruct: 38.9 (#188)
| Benchmark | Qwen Plus | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Longer Query | 1324 | 1282 |
Writing & Preference Qwen Plus leads
Qwen Plus: 52.2 (#176), Qwen2.5 72B Instruct: 46.7 (#215)
| Benchmark | Qwen Plus | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Text | 1326 | 1269 |
| LMArena Creative Writing | 1293 | 1221 |
| LMArena Multi-Turn | 1336 | 1272 |
| WildBench | — | 80.2% |
Frequently asked questions
Is Qwen Plus better than Qwen2.5 72B Instruct?
Qwen Plus is the stronger model overall, scoring 37.1 to 31.9 on the Noometry Index.
Which is cheaper, Qwen Plus or Qwen2.5 72B Instruct?
Qwen Plus is cheaper. It lists at $0.40 per million input tokens and $1.20 per million output tokens; Qwen2.5 72B Instruct lists at $1.40 and $5.60.
Is Qwen Plus or Qwen2.5 72B Instruct better for coding?
Qwen Plus scores higher on coding benchmarks: 38.9 versus 33.2 in the Noometry coding category.
Which has the bigger context window?
Qwen Plus does, with 1M tokens against 131K.
How many benchmarks do Qwen Plus and Qwen2.5 72B Instruct share?
18 benchmarks have published results for both models. Qwen Plus has 20 scored results on Noometry and Qwen2.5 72B Instruct has 43.