Model comparison
Qwen2.5 14B Instruct vs Qwen2.5-Coder-32B
Qwen2.5-Coder-32B has enough public results to be ranked (#245); Qwen2.5 14B Instruct does not yet, so treat this comparison as directional.
Last verified . 3 shared benchmarks.
Alibaba (Qwen)Summary
- They share 3 benchmarks with published results for both. Qwen2.5 14B Instruct scores higher in 1 category and Qwen2.5-Coder-32B in 0 categories; one gap is clear of the uncertainty.
- The widest gap is in coding, where Qwen2.5 14B Instruct leads 37.7 to 22.6.
- The biggest single-benchmark swing is BigCodeBench Instruct: 39.8% for Qwen2.5 14B Instruct and 49% for Qwen2.5-Coder-32B.
- Qwen2.5 14B Instruct is cheaper at $0.35 / $1.40 per million input/output tokens, against $0.66 / $1 for Qwen2.5-Coder-32B.
- Qwen2.5 14B Instruct accepts more context: 131K tokens versus 33K.
Side by side
| Qwen2.5 14B Instruct | Qwen2.5-Coder-32B | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 38.7 | 33.4 |
| Released | 2024-09 | 2024-09-18 |
| Weights | Open | Open |
| Context window | 131K | 33K |
| Max output | 8K | 29K |
| Input $ / M tokens | $0.35 | $0.66 |
| Output $ / M tokens | $1.40 | $1 |
| Results tracked | 3 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5 14B Instruct leads
Qwen2.5 14B Instruct: 37.7 (#191), Qwen2.5-Coder-32B: 22.6 (#333)
| Benchmark | Qwen2.5 14B Instruct | Qwen2.5-Coder-32B |
|---|---|---|
| BigCodeBench Instruct | 39.8% | 49% |
| BigCodeBench Complete | 52.2% | 58% |
| SWE-bench Verified (bash only) | — | 9% |
| Aider Polyglot | — | 16.4% |
| LiveBench Coding | — | 56.9% |
| LMArena Coding | — | 1276 |
| HumanEval+ | — | 87.2% |
| MBPP+ | — | 77% |
Reasoning Not comparable
Qwen2.5 14B Instruct: —, Qwen2.5-Coder-32B: 21.2 (#225)
| Benchmark | Qwen2.5 14B Instruct | Qwen2.5-Coder-32B |
|---|---|---|
| LiveBench Reasoning | — | 42.1% |
| LMArena Hard Prompts | — | 1251 |
| LiveBench Data Analysis | — | 49.9% |
| Epoch Capabilities Index | — | 119.49 |
| HellaSwag | — | 83% |
| LiveBench | — | 46.2% |
| WinoGrande | — | 80.8% |
Math Not comparable
Qwen2.5 14B Instruct: —, Qwen2.5-Coder-32B: 33.3 (#204)
| Benchmark | Qwen2.5 14B Instruct | Qwen2.5-Coder-32B |
|---|---|---|
| LiveBench Math | — | 46.6% |
| LMArena Math | — | 1251 |
| GSM8K | — | 93% |
Knowledge Not comparable
Qwen2.5 14B Instruct: —, Qwen2.5-Coder-32B: 33.4 (#203)
| Benchmark | Qwen2.5 14B Instruct | Qwen2.5-Coder-32B |
|---|---|---|
| MMLU | 79.9% | 79.1% |
| LMArena Expert | — | 1221 |
| ARC (AI2) Challenge | — | 70.5% |
Multilingual Not comparable
Qwen2.5 14B Instruct: —, Qwen2.5-Coder-32B: 37.8 (#235)
| Benchmark | Qwen2.5 14B Instruct | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Non-English | — | 1205 |
| LMArena Chinese | — | 1222 |
| LMArena Russian | — | 1228 |
Instruction Following Not comparable
Qwen2.5 14B Instruct: —, Qwen2.5-Coder-32B: 61.4 (#245)
| Benchmark | Qwen2.5 14B Instruct | Qwen2.5-Coder-32B |
|---|---|---|
| LiveBench Instruction Following | — | 58.7% |
| LMArena Instruction Following | — | 1223 |
Long Context Not comparable
Qwen2.5 14B Instruct: —, Qwen2.5-Coder-32B: 38.0 (#208)
| Benchmark | Qwen2.5 14B Instruct | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Longer Query | — | 1251 |
Writing & Preference Not comparable
Qwen2.5 14B Instruct: —, Qwen2.5-Coder-32B: 41.6 (#240)
| Benchmark | Qwen2.5 14B Instruct | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Text | — | 1230 |
| LMArena Creative Writing | — | 1174 |
| LMArena Multi-Turn | — | 1222 |
| LiveBench Language | — | 23.3% |
Frequently asked questions
Is Qwen2.5 14B Instruct better than Qwen2.5-Coder-32B?
Qwen2.5-Coder-32B has enough public results to be ranked (#245); Qwen2.5 14B Instruct does not yet, so treat this comparison as directional.
Which is cheaper, Qwen2.5 14B Instruct or Qwen2.5-Coder-32B?
Qwen2.5 14B Instruct is cheaper. It lists at $0.35 per million input tokens and $1.40 per million output tokens; Qwen2.5-Coder-32B lists at $0.66 and $1.
Is Qwen2.5 14B Instruct or Qwen2.5-Coder-32B better for coding?
Qwen2.5 14B Instruct scores higher on coding benchmarks: 37.7 versus 22.6 in the Noometry coding category.
Which has the bigger context window?
Qwen2.5 14B Instruct does, with 131K tokens against 33K.
How many benchmarks do Qwen2.5 14B Instruct and Qwen2.5-Coder-32B share?
3 benchmarks have published results for both models. Qwen2.5 14B Instruct has 3 scored results on Noometry and Qwen2.5-Coder-32B has 31.