Model comparison
Qwen1.5-14B vs Qwen2.5 32B Instruct
Qwen1.5-14B is the stronger model overall, scoring 32.7 to 30.1 on the Noometry Index.
Last verified . 0 shared benchmarks.
Alibaba (Qwen)Summary
- The widest gap is in math, where Qwen1.5-14B leads 32.4 to 16.2.
Side by side
| Qwen1.5-14B | Qwen2.5 32B Instruct | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 32.7 | 30.1 |
| Released | 2024-02-04 | 2024-09 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 8K |
| Input $ / M tokens | — | $0.70 |
| Output $ / M tokens | — | $2.80 |
| Results tracked | 17 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5 32B Instruct leads
Qwen1.5-14B: 33.1 (#263), Qwen2.5 32B Instruct: 38.7 (#169)
| Benchmark | Qwen1.5-14B | Qwen2.5 32B Instruct |
|---|---|---|
| BigCodeBench Instruct | — | 45% |
| LMArena Coding | 1138 | — |
| BigCodeBench Complete | — | 52.3% |
Reasoning Qwen1.5-14B leads
Qwen1.5-14B: 21.4 (#223), Qwen2.5 32B Instruct: 19.2 (#266)
| Benchmark | Qwen1.5-14B | Qwen2.5 32B Instruct |
|---|---|---|
| Chess Puzzles | — | 0% |
| LMArena Hard Prompts | 1113 | — |
| Epoch Capabilities Index | — | 128.52 |
Math Qwen1.5-14B leads
Qwen1.5-14B: 32.4 (#215), Qwen2.5 32B Instruct: 16.2 (#296)
| Benchmark | Qwen1.5-14B | Qwen2.5 32B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 7.4% |
| LMArena Math | 1125 | — |
| MATH Level 5 | — | 56.1% |
Knowledge Qwen1.5-14B leads
Qwen1.5-14B: 29.8 (#232), Qwen2.5 32B Instruct: 24.9 (#266)
| Benchmark | Qwen1.5-14B | Qwen2.5 32B Instruct |
|---|---|---|
| GPQA Diamond | — | 46.1% |
| LMArena Expert | 1094 | — |
| MMLU | 68.6% | — |
Multilingual Not comparable
Qwen1.5-14B: 30.7 (#262), Qwen2.5 32B Instruct: —
| Benchmark | Qwen1.5-14B | Qwen2.5 32B Instruct |
|---|---|---|
| LMArena Non-English | 1095 | — |
| LMArena Chinese | 1147 | — |
| LMArena French | 1116 | — |
| LMArena German | 1043 | — |
| LMArena Japanese | 1019 | — |
| LMArena Russian | 1046 | — |
| LMArena Spanish | 1085 | — |
Instruction Following Not comparable
Qwen1.5-14B: 56.8 (#271), Qwen2.5 32B Instruct: —
| Benchmark | Qwen1.5-14B | Qwen2.5 32B Instruct |
|---|---|---|
| LMArena Instruction Following | 1102 | — |
Long Context Not comparable
Qwen1.5-14B: 33.7 (#257), Qwen2.5 32B Instruct: —
| Benchmark | Qwen1.5-14B | Qwen2.5 32B Instruct |
|---|---|---|
| LMArena Longer Query | 1113 | — |
Writing & Preference Not comparable
Qwen1.5-14B: 33.6 (#276), Qwen2.5 32B Instruct: —
| Benchmark | Qwen1.5-14B | Qwen2.5 32B Instruct |
|---|---|---|
| LMArena Text | 1128 | — |
| LMArena Creative Writing | 1091 | — |
| LMArena Multi-Turn | 1110 | — |
Frequently asked questions
Is Qwen1.5-14B better than Qwen2.5 32B Instruct?
Qwen1.5-14B is the stronger model overall, scoring 32.7 to 30.1 on the Noometry Index.
Is Qwen1.5-14B or Qwen2.5 32B Instruct better for coding?
Qwen2.5 32B Instruct scores higher on coding benchmarks: 38.7 versus 33.1 in the Noometry coding category.
How many benchmarks do Qwen1.5-14B and Qwen2.5 32B Instruct share?
0 benchmarks have published results for both models. Qwen1.5-14B has 17 scored results on Noometry and Qwen2.5 32B Instruct has 7.