Model comparison
Qwen1.5-7B vs Qwen2.5 72B Instruct
Qwen1.5-7B and Qwen2.5 72B Instruct score almost the same on the Noometry Index (30.8 vs 31.5), so choose on price, context window or the category you care about most.
Last verified . 13 shared benchmarks.
Alibaba (Qwen)Summary
- They share 13 benchmarks with published results for both. Qwen1.5-7B scores higher in 2 categories and Qwen2.5 72B Instruct in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen2.5 72B Instruct leads 46.9 to 29.8.
Side by side
| Qwen1.5-7B | Qwen2.5 72B Instruct | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 30.8 | 31.5 |
| Released | 2024-02-04 | 2024-09 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 8K |
| Input $ / M tokens | — | $1.40 |
| Output $ / M tokens | — | $5.60 |
| Results tracked | 13 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5 72B Instruct leads
Qwen1.5-7B: 31.6 (#271), Qwen2.5 72B Instruct: 32.8 (#256)
| Benchmark | Qwen1.5-7B | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Coding | 1107 | 1293 |
| WeirdML | — | 16% |
| BigCodeBench Instruct | — | 45.8% |
| BigCodeBench Complete | — | 55.9% |
Agentic & Tool Use Not comparable
Qwen1.5-7B: —, Qwen2.5 72B Instruct: 22.0 (#124)
| Benchmark | Qwen1.5-7B | Qwen2.5 72B Instruct |
|---|---|---|
| TheAgentCompany | — | 5.7% |
| BALROG | — | 16.2% |
| METR Time Horizons | — | 35.8% |
Reasoning Qwen2.5 72B Instruct leads
Qwen1.5-7B: 19.5 (#237), Qwen2.5 72B Instruct: 21.4 (#197)
| Benchmark | Qwen1.5-7B | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1066 | 1271 |
| 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 Qwen1.5-7B leads
Qwen1.5-7B: 29.0 (#222), Qwen2.5 72B Instruct: 18.1 (#281)
| Benchmark | Qwen1.5-7B | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Math | 1080 | 1283 |
| OTIS Mock AIME 2024-2025 | — | 8.1% |
| Omni-MATH | — | 33% |
| MATH Level 5 | — | 63.2% |
Knowledge Qwen1.5-7B leads
Qwen1.5-7B: 28.2 (#239), Qwen2.5 72B Instruct: 26.9 (#247)
| Benchmark | Qwen1.5-7B | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Expert | 1055 | 1245 |
| MMLU | 62.6% | 85.3% |
| GPQA Diamond | — | 49.1% |
| MMLU-Pro | — | 63.1% |
| Confabulations | — | 19.1% |
| GPQA (HELM) | — | 42.6% |
| ARC (AI2) Challenge | — | 94.5% |
| TriviaQA | — | 71.9% |
Multilingual Qwen2.5 72B Instruct leads
Qwen1.5-7B: 28.6 (#266), Qwen2.5 72B Instruct: 41.2 (#208)
| Benchmark | Qwen1.5-7B | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Non-English | 1058 | 1252 |
| LMArena Chinese | 1140 | 1272 |
| LMArena Russian | 1006 | 1264 |
| LMArena French | — | 1279 |
| LMArena German | — | 1234 |
| LMArena Japanese | — | 1180 |
| LMArena Korean | — | 1188 |
| LMArena Spanish | — | 1255 |
Instruction Following Qwen2.5 72B Instruct leads
Qwen1.5-7B: 54.4 (#276), Qwen2.5 72B Instruct: 65.7 (#216)
| Benchmark | Qwen1.5-7B | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Instruction Following | 1058 | 1254 |
| IFEval | — | 80.6% |
Long Context Qwen2.5 72B Instruct leads
Qwen1.5-7B: 33.1 (#261), Qwen2.5 72B Instruct: 38.9 (#183)
| Benchmark | Qwen1.5-7B | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Longer Query | 1090 | 1282 |
Writing & Preference Qwen2.5 72B Instruct leads
Qwen1.5-7B: 29.8 (#288), Qwen2.5 72B Instruct: 46.9 (#210)
| Benchmark | Qwen1.5-7B | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Text | 1084 | 1269 |
| LMArena Creative Writing | 1035 | 1221 |
| LMArena Multi-Turn | 1061 | 1272 |
| WildBench | — | 80.2% |
Frequently asked questions
Is Qwen1.5-7B better than Qwen2.5 72B Instruct?
Qwen1.5-7B and Qwen2.5 72B Instruct score almost the same on the Noometry Index (30.8 vs 31.5), so choose on price, context window or the category you care about most.
Is Qwen1.5-7B or Qwen2.5 72B Instruct better for coding?
Qwen2.5 72B Instruct scores higher on coding benchmarks: 32.8 versus 31.6 in the Noometry coding category.
How many benchmarks do Qwen1.5-7B and Qwen2.5 72B Instruct share?
13 benchmarks have published results for both models. Qwen1.5-7B has 13 scored results on Noometry and Qwen2.5 72B Instruct has 43.