Model comparison
Qwen2.5 32B Instruct vs Qwen2-72B
Qwen2.5 32B Instruct and Qwen2-72B score almost the same on the Noometry Index (30.1 vs 30.0), so choose on price, context window or the category you care about most.
Last verified . 5 shared benchmarks.
Alibaba (Qwen)Summary
- They share 5 benchmarks with published results for both. Qwen2.5 32B Instruct scores higher in 2 categories and Qwen2-72B in 2 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen2-72B leads 30.2 to 16.2.
- The biggest single-benchmark swing is MATH Level 5: 56.1% for Qwen2.5 32B Instruct and 39.1% for Qwen2-72B.
Side by side
| Qwen2.5 32B Instruct | Qwen2-72B | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 30.1 | 30.0 |
| Released | 2024-09 | 2024-06-07 |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.70 | — |
| Output $ / M tokens | $2.80 | — |
| Results tracked | 7 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5 32B Instruct leads
Qwen2.5 32B Instruct: 38.7 (#169), Qwen2-72B: 29.1 (#310)
| Benchmark | Qwen2.5 32B Instruct | Qwen2-72B |
|---|---|---|
| BigCodeBench Instruct | 45% | 38.5% |
| BigCodeBench Complete | 52.3% | 54% |
| WeirdML | — | 11.3% |
| LMArena Coding | — | 1196 |
Agentic & Tool Use Not comparable
Qwen2.5 32B Instruct: —, Qwen2-72B: 17.0 (#146)
| Benchmark | Qwen2.5 32B Instruct | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |
Reasoning Qwen2-72B leads
Qwen2.5 32B Instruct: 19.2 (#266), Qwen2-72B: 23.2 (#181)
| Benchmark | Qwen2.5 32B Instruct | Qwen2-72B |
|---|---|---|
| Epoch Capabilities Index | 128.52 | 125.28 |
| Chess Puzzles | 0% | — |
| LMArena Hard Prompts | — | 1191 |
Math Qwen2-72B leads
Qwen2.5 32B Instruct: 16.2 (#296), Qwen2-72B: 30.2 (#236)
| Benchmark | Qwen2.5 32B Instruct | Qwen2-72B |
|---|---|---|
| MATH Level 5 | 56.1% | 39.1% |
| OTIS Mock AIME 2024-2025 | 7.4% | — |
| LMArena Math | — | 1235 |
Knowledge Qwen2.5 32B Instruct leads
Qwen2.5 32B Instruct: 24.9 (#266), Qwen2-72B: 21.2 (#275)
| Benchmark | Qwen2.5 32B Instruct | Qwen2-72B |
|---|---|---|
| GPQA Diamond | 46.1% | 40.8% |
| LMArena Expert | — | 1171 |
| MMLU | — | 82.4% |
Multilingual Not comparable
Qwen2.5 32B Instruct: —, Qwen2-72B: 35.9 (#244)
| Benchmark | Qwen2.5 32B Instruct | Qwen2-72B |
|---|---|---|
| LMArena Non-English | — | 1176 |
| LMArena Chinese | — | 1240 |
| LMArena French | — | 1170 |
| LMArena German | — | 1151 |
| LMArena Japanese | — | 1111 |
| LMArena Korean | — | 1083 |
| LMArena Russian | — | 1169 |
| LMArena Spanish | — | 1169 |
Instruction Following Not comparable
Qwen2.5 32B Instruct: —, Qwen2-72B: 61.7 (#241)
| Benchmark | Qwen2.5 32B Instruct | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | — | 1181 |
Long Context Not comparable
Qwen2.5 32B Instruct: —, Qwen2-72B: 36.1 (#235)
| Benchmark | Qwen2.5 32B Instruct | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | — | 1192 |
Writing & Preference Not comparable
Qwen2.5 32B Instruct: —, Qwen2-72B: 40.8 (#241)
| Benchmark | Qwen2.5 32B Instruct | Qwen2-72B |
|---|---|---|
| LMArena Text | — | 1203 |
| LMArena Creative Writing | — | 1181 |
| LMArena Multi-Turn | — | 1196 |
Frequently asked questions
Is Qwen2.5 32B Instruct better than Qwen2-72B?
Qwen2.5 32B Instruct and Qwen2-72B score almost the same on the Noometry Index (30.1 vs 30.0), so choose on price, context window or the category you care about most.
Is Qwen2.5 32B Instruct or Qwen2-72B better for coding?
Qwen2.5 32B Instruct scores higher on coding benchmarks: 38.7 versus 29.1 in the Noometry coding category.
How many benchmarks do Qwen2.5 32B Instruct and Qwen2-72B share?
5 benchmarks have published results for both models. Qwen2.5 32B Instruct has 7 scored results on Noometry and Qwen2-72B has 26.