Model comparison
Qwen1.5-72B vs Qwen2-72B
Qwen1.5-72B and Qwen2-72B score almost the same on the Noometry Index (30.3 vs 29.5), so choose on price, context window or the category you care about most.
Last verified . 20 shared benchmarks.
Alibaba (Qwen)Summary
- They share 20 benchmarks with published results for both. Qwen1.5-72B scores higher in 2 categories and Qwen2-72B in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen2-72B leads 21.2 to 11.5.
- The biggest single-benchmark swing is BigCodeBench Complete: 40.3% for Qwen1.5-72B and 54% for Qwen2-72B.
Side by side
| Qwen1.5-72B | Qwen2-72B | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 30.3 | 29.5 |
| Released | 2024-02-04 | 2024-06-07 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 22 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen1.5-72B leads
Qwen1.5-72B: 31.4 (#272), Qwen2-72B: 28.7 (#303)
| Benchmark | Qwen1.5-72B | Qwen2-72B |
|---|---|---|
| BigCodeBench Instruct | 33.2% | 38.5% |
| LMArena Coding | 1166 | 1196 |
| BigCodeBench Complete | 40.3% | 54% |
| WeirdML | — | 11.3% |
| HumanEval+ | 59.1% | — |
| MBPP+ | 61.6% | — |
Agentic & Tool Use Not comparable
Qwen1.5-72B: —, Qwen2-72B: 16.9 (#138)
| Benchmark | Qwen1.5-72B | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |
Reasoning Too close to call
Qwen1.5-72B: 21.2 (#201), Qwen2-72B: 22.2 (#184)
| Benchmark | Qwen1.5-72B | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1148 | 1191 |
| Epoch Capabilities Index | — | 125.27 |
Math Qwen1.5-72B leads
Qwen1.5-72B: 30.7 (#205), Qwen2-72B: 27.9 (#232)
| Benchmark | Qwen1.5-72B | Qwen2-72B |
|---|---|---|
| LMArena Math | 1164 | 1235 |
| MATH Level 5 | — | 39.1% |
Knowledge Qwen2-72B leads
Qwen1.5-72B: 11.5 (#295), Qwen2-72B: 21.2 (#270)
| Benchmark | Qwen1.5-72B | Qwen2-72B |
|---|---|---|
| GPQA Diamond | 28.8% | 40.8% |
| LMArena Expert | 1136 | 1171 |
| MMLU | — | 82.4% |
Multilingual Qwen2-72B leads
Qwen1.5-72B: 33.4 (#248), Qwen2-72B: 36.0 (#239)
| Benchmark | Qwen1.5-72B | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1135 | 1176 |
| LMArena Chinese | 1186 | 1240 |
| LMArena French | 1158 | 1169 |
| LMArena German | 1084 | 1151 |
| LMArena Japanese | 1061 | 1111 |
| LMArena Korean | 1049 | 1083 |
| LMArena Russian | 1104 | 1169 |
| LMArena Spanish | 1110 | 1168 |
Instruction Following Qwen2-72B leads
Qwen1.5-72B: 59.6 (#251), Qwen2-72B: 62.0 (#236)
| Benchmark | Qwen1.5-72B | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1142 | 1181 |
Long Context Qwen2-72B leads
Qwen1.5-72B: 35.0 (#238), Qwen2-72B: 36.1 (#230)
| Benchmark | Qwen1.5-72B | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1157 | 1193 |
Writing & Preference Qwen2-72B leads
Qwen1.5-72B: 37.4 (#253), Qwen2-72B: 41.0 (#236)
| Benchmark | Qwen1.5-72B | Qwen2-72B |
|---|---|---|
| LMArena Text | 1166 | 1203 |
| LMArena Creative Writing | 1137 | 1181 |
| LMArena Multi-Turn | 1160 | 1195 |
Frequently asked questions
Is Qwen1.5-72B better than Qwen2-72B?
Qwen1.5-72B and Qwen2-72B score almost the same on the Noometry Index (30.3 vs 29.5), so choose on price, context window or the category you care about most.
Is Qwen1.5-72B or Qwen2-72B better for coding?
Qwen1.5-72B scores higher on coding benchmarks: 31.4 versus 28.7 in the Noometry coding category.
How many benchmarks do Qwen1.5-72B and Qwen2-72B share?
20 benchmarks have published results for both models. Qwen1.5-72B has 22 scored results on Noometry and Qwen2-72B has 26.