Model comparison
Qwen1.5-32B vs Qwen2.5 7B Instruct
Qwen1.5-32B is the stronger model overall, scoring 30.0 to 28.6 on the Noometry Index.
Last verified . 4 shared benchmarks.
Alibaba (Qwen)Summary
- They share 4 benchmarks with published results for both. Qwen1.5-32B scores higher in 2 categories and Qwen2.5 7B Instruct in 4 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen1.5-32B leads 30.5 to 11.8.
- The biggest single-benchmark swing is BigCodeBench Instruct: 32.3% for Qwen1.5-32B and 37.6% for Qwen2.5 7B Instruct.
Side by side
| Qwen1.5-32B | Qwen2.5 7B Instruct | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 30.0 | 28.6 |
| Released | 2024-02-04 | 2024-09 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 8K |
| Input $ / M tokens | — | $0.17 |
| Output $ / M tokens | — | $0.70 |
| Results tracked | 21 | 15 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5 7B Instruct leads
Qwen1.5-32B: 31.1 (#278), Qwen2.5 7B Instruct: 35.9 (#204)
| Benchmark | Qwen1.5-32B | Qwen2.5 7B Instruct |
|---|---|---|
| BigCodeBench Instruct | 32.3% | 37.6% |
| BigCodeBench Complete | 42% | 46.1% |
| LMArena Coding | 1155 | — |
Agentic & Tool Use Not comparable
Qwen1.5-32B: —, Qwen2.5 7B Instruct: 23.5 (#117)
| Benchmark | Qwen1.5-32B | Qwen2.5 7B Instruct |
|---|---|---|
| BALROG | — | 7.8% |
Reasoning Qwen1.5-32B leads
Qwen1.5-32B: 20.9 (#210), Qwen2.5 7B Instruct: 14.3 (#317)
| Benchmark | Qwen1.5-32B | Qwen2.5 7B Instruct |
|---|---|---|
| Chess Puzzles | — | 0% |
| LMArena Hard Prompts | 1131 | — |
| DTBench | — | 47.7% |
| LMCA | — | 6.4% |
| Epoch Capabilities Index | — | 118.44 |
Math Qwen1.5-32B leads
Qwen1.5-32B: 30.5 (#207), Qwen2.5 7B Instruct: 11.8 (#300)
| Benchmark | Qwen1.5-32B | Qwen2.5 7B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 2.5% |
| Omni-MATH | — | 29.4% |
| LMArena Math | 1155 | — |
Knowledge Qwen2.5 7B Instruct leads
Qwen1.5-32B: 13.5 (#291), Qwen2.5 7B Instruct: 17.0 (#281)
| Benchmark | Qwen1.5-32B | Qwen2.5 7B Instruct |
|---|---|---|
| GPQA Diamond | 30.7% | 35.5% |
| MMLU | 74.4% | 72.9% |
| MMLU-Pro | — | 53.9% |
| GPQA (HELM) | — | 34.1% |
| LMArena Expert | 1126 | — |
Multilingual Not comparable
Qwen1.5-32B: 31.6 (#254), Qwen2.5 7B Instruct: —
| Benchmark | Qwen1.5-32B | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Non-English | 1106 | — |
| LMArena Chinese | 1176 | — |
| LMArena French | 1100 | — |
| LMArena German | 1058 | — |
| LMArena Japanese | 1027 | — |
| LMArena Korean | 1007 | — |
| LMArena Russian | 1073 | — |
| LMArena Spanish | 1089 | — |
Instruction Following Qwen2.5 7B Instruct leads
Qwen1.5-32B: 58.0 (#260), Qwen2.5 7B Instruct: 63.4 (#226)
| Benchmark | Qwen1.5-32B | Qwen2.5 7B Instruct |
|---|---|---|
| IFEval | — | 74.1% |
| LMArena Instruction Following | 1116 | — |
Long Context Not comparable
Qwen1.5-32B: 34.7 (#241), Qwen2.5 7B Instruct: —
| Benchmark | Qwen1.5-32B | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Longer Query | 1146 | — |
Writing & Preference Qwen2.5 7B Instruct leads
Qwen1.5-32B: 34.4 (#266), Qwen2.5 7B Instruct: 48.8 (#194)
| Benchmark | Qwen1.5-32B | Qwen2.5 7B Instruct |
|---|---|---|
| LMArena Text | 1137 | — |
| LMArena Creative Writing | 1083 | — |
| WildBench | — | 73.1% |
| LMArena Multi-Turn | 1140 | — |
Frequently asked questions
Is Qwen1.5-32B better than Qwen2.5 7B Instruct?
Qwen1.5-32B is the stronger model overall, scoring 30.0 to 28.6 on the Noometry Index.
Is Qwen1.5-32B or Qwen2.5 7B Instruct better for coding?
Qwen2.5 7B Instruct scores higher on coding benchmarks: 35.9 versus 31.1 in the Noometry coding category.
How many benchmarks do Qwen1.5-32B and Qwen2.5 7B Instruct share?
4 benchmarks have published results for both models. Qwen1.5-32B has 21 scored results on Noometry and Qwen2.5 7B Instruct has 15.