Model comparison
Qwen2.5 72B Instruct vs Qwen2.5 Plus 1127
Qwen2.5 Plus 1127 is the stronger model overall, scoring 38.1 to 31.5 on the Noometry Index.
Last verified . 14 shared benchmarks.
Alibaba (Qwen)Summary
- They share 14 benchmarks with published results for both. Qwen2.5 72B Instruct scores higher in 0 categories and Qwen2.5 Plus 1127 in 8 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen2.5 Plus 1127 leads 33.5 to 18.1.
- Qwen2.5 72B Instruct has downloadable open weights; the other is API-only.
Side by side
| Qwen2.5 72B Instruct | Qwen2.5 Plus 1127 | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 31.5 | 38.1 |
| Released | 2024-09 | — |
| Weights | Open | Proprietary |
| Context window | 131K | — |
| Max output | 8K | — |
| Input $ / M tokens | $1.40 | — |
| Output $ / M tokens | $5.60 | — |
| Results tracked | 43 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5 Plus 1127 leads
Qwen2.5 72B Instruct: 32.8 (#256), Qwen2.5 Plus 1127: 37.9 (#171)
| Benchmark | Qwen2.5 72B Instruct | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Coding | 1293 | 1314 |
| WeirdML | 16% | — |
| BigCodeBench Instruct | 45.8% | — |
| BigCodeBench Complete | 55.9% | — |
Agentic & Tool Use Not comparable
Qwen2.5 72B Instruct: 22.0 (#124), Qwen2.5 Plus 1127: —
| Benchmark | Qwen2.5 72B Instruct | Qwen2.5 Plus 1127 |
|---|---|---|
| TheAgentCompany | 5.7% | — |
| BALROG | 16.2% | — |
| METR Time Horizons | 35.8% | — |
Reasoning Qwen2.5 Plus 1127 leads
Qwen2.5 72B Instruct: 21.4 (#197), Qwen2.5 Plus 1127: 24.8 (#139)
| Benchmark | Qwen2.5 72B Instruct | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Hard Prompts | 1271 | 1299 |
| 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 Qwen2.5 Plus 1127 leads
Qwen2.5 72B Instruct: 18.1 (#281), Qwen2.5 Plus 1127: 33.5 (#175)
| Benchmark | Qwen2.5 72B Instruct | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Math | 1283 | 1298 |
| OTIS Mock AIME 2024-2025 | 8.1% | — |
| Omni-MATH | 33% | — |
| MATH Level 5 | 63.2% | — |
Knowledge Qwen2.5 Plus 1127 leads
Qwen2.5 72B Instruct: 26.9 (#247), Qwen2.5 Plus 1127: 34.9 (#179)
| Benchmark | Qwen2.5 72B Instruct | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Expert | 1245 | 1289 |
| GPQA Diamond | 49.1% | — |
| MMLU-Pro | 63.1% | — |
| Confabulations | 19.1% | — |
| GPQA (HELM) | 42.6% | — |
| ARC (AI2) Challenge | 94.5% | — |
| MMLU | 85.3% | — |
| TriviaQA | 71.9% | — |
Multilingual Too close to call
Qwen2.5 72B Instruct: 41.2 (#208), Qwen2.5 Plus 1127: 42.1 (#196)
| Benchmark | Qwen2.5 72B Instruct | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Non-English | 1252 | 1265 |
| LMArena Chinese | 1272 | 1314 |
| LMArena German | 1234 | 1231 |
| LMArena Japanese | 1180 | 1207 |
| LMArena Russian | 1264 | 1271 |
| LMArena French | 1279 | — |
| LMArena Korean | 1188 | — |
| LMArena Spanish | 1255 | — |
Instruction Following Qwen2.5 Plus 1127 leads
Qwen2.5 72B Instruct: 65.7 (#216), Qwen2.5 Plus 1127: 67.4 (#194)
| Benchmark | Qwen2.5 72B Instruct | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Instruction Following | 1254 | 1275 |
| IFEval | 80.6% | — |
Long Context Too close to call
Qwen2.5 72B Instruct: 38.9 (#183), Qwen2.5 Plus 1127: 39.2 (#180)
| Benchmark | Qwen2.5 72B Instruct | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Longer Query | 1282 | 1292 |
Writing & Preference Qwen2.5 Plus 1127 leads
Qwen2.5 72B Instruct: 46.9 (#210), Qwen2.5 Plus 1127: 49.5 (#186)
| Benchmark | Qwen2.5 72B Instruct | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Text | 1269 | 1299 |
| LMArena Creative Writing | 1221 | 1262 |
| LMArena Multi-Turn | 1272 | 1299 |
| WildBench | 80.2% | — |
Frequently asked questions
Is Qwen2.5 72B Instruct better than Qwen2.5 Plus 1127?
Qwen2.5 Plus 1127 is the stronger model overall, scoring 38.1 to 31.5 on the Noometry Index.
Is Qwen2.5 72B Instruct or Qwen2.5 Plus 1127 better for coding?
Qwen2.5 Plus 1127 scores higher on coding benchmarks: 37.9 versus 32.8 in the Noometry coding category.
How many benchmarks do Qwen2.5 72B Instruct and Qwen2.5 Plus 1127 share?
14 benchmarks have published results for both models. Qwen2.5 72B Instruct has 43 scored results on Noometry and Qwen2.5 Plus 1127 has 14.