Model comparison
Qwen2.5-Coder-32B vs Qwen3 14B
Qwen3 14B is the stronger model overall, scoring 35.0 to 32.9 on the Noometry Index.
Last verified . 1 shared benchmarks.
Alibaba (Qwen)Summary
- They share 1 benchmark with published results for both. Qwen2.5-Coder-32B scores higher in 1 category and Qwen3 14B in 4 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in coding, where Qwen3 14B leads 36.7 to 22.4.
- Qwen3 14B is cheaper at $0.35 / $1.40 per million input/output tokens, against $0.66 / $1 for Qwen2.5-Coder-32B.
- Qwen3 14B accepts more context: 131K tokens versus 33K.
Side by side
| Qwen2.5-Coder-32B | Qwen3 14B | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 32.9 | 35.0 |
| Released | 2024-09-18 | 2025-04 |
| Weights | Open | Open |
| Context window | 33K | 131K |
| Max output | 29K | 8K |
| Input $ / M tokens | $0.66 | $0.35 |
| Output $ / M tokens | $1 | $1.40 |
| Results tracked | 31 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 14B leads
Qwen2.5-Coder-32B: 22.4 (#328), Qwen3 14B: 36.7 (#191)
| Benchmark | Qwen2.5-Coder-32B | Qwen3 14B |
|---|---|---|
| SWE-bench Verified (bash only) | 9% | — |
| Aider Polyglot | 16.4% | — |
| SciCode | — | 31.6% |
| BigCodeBench Instruct | 49% | — |
| LiveBench Coding | 56.9% | — |
| LMArena Coding | 1276 | — |
| BigCodeBench Complete | 58% | — |
| HumanEval+ | 87.2% | — |
| MBPP+ | 77% | — |
Agentic & Tool Use Not comparable
Qwen2.5-Coder-32B: —, Qwen3 14B: 29.4 (#78)
| Benchmark | Qwen2.5-Coder-32B | Qwen3 14B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 41% |
Reasoning Qwen2.5-Coder-32B leads
Qwen2.5-Coder-32B: 20.4 (#220), Qwen3 14B: 18.1 (#272)
| Benchmark | Qwen2.5-Coder-32B | Qwen3 14B |
|---|---|---|
| Epoch Capabilities Index | 119.41 | 138.23 |
| Kagi LLM Benchmark | — | 49.1% |
| CritPt | — | 0% |
| Chess Puzzles | — | 4% |
| LiveBench Reasoning | 42.1% | — |
| LMArena Hard Prompts | 1251 | — |
| DTBench | — | 64% |
| LiveBench Data Analysis | 49.9% | — |
| LMCA | — | 18.2% |
| HellaSwag | 83% | — |
| LiveBench | 46.2% | — |
| WinoGrande | 80.8% | — |
Math Qwen3 14B leads
Qwen2.5-Coder-32B: 30.8 (#203), Qwen3 14B: 37.0 (#102)
| Benchmark | Qwen2.5-Coder-32B | Qwen3 14B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 66.4% |
| LiveBench Math | 46.6% | — |
| LMArena Math | 1251 | — |
| GSM8K | 93% | — |
Knowledge Qwen3 14B leads
Qwen2.5-Coder-32B: 32.9 (#200), Qwen3 14B: 39.2 (#124)
| Benchmark | Qwen2.5-Coder-32B | Qwen3 14B |
|---|---|---|
| GPQA Diamond | — | 63.8% |
| Vectara Hallucination Rate | — | 5.4% |
| LMArena Expert | 1221 | — |
| ARC (AI2) Challenge | 70.5% | — |
| MMLU | 79.1% | — |
Multilingual Not comparable
Qwen2.5-Coder-32B: 38.0 (#230), Qwen3 14B: —
| Benchmark | Qwen2.5-Coder-32B | Qwen3 14B |
|---|---|---|
| LMArena Non-English | 1205 | — |
| LMArena Chinese | 1222 | — |
| LMArena Russian | 1228 | — |
Instruction Following Not comparable
Qwen2.5-Coder-32B: 61.6 (#240), Qwen3 14B: —
| Benchmark | Qwen2.5-Coder-32B | Qwen3 14B |
|---|---|---|
| LiveBench Instruction Following | 58.7% | — |
| LMArena Instruction Following | 1223 | — |
Long Context Too close to call
Qwen2.5-Coder-32B: 37.9 (#204), Qwen3 14B: 38.0 (#201)
| Benchmark | Qwen2.5-Coder-32B | Qwen3 14B |
|---|---|---|
| Fiction.LiveBench | — | 62.5% |
| LMArena Longer Query | 1251 | — |
Writing & Preference Not comparable
Qwen2.5-Coder-32B: 41.8 (#235), Qwen3 14B: —
| Benchmark | Qwen2.5-Coder-32B | Qwen3 14B |
|---|---|---|
| LMArena Text | 1230 | — |
| LMArena Creative Writing | 1174 | — |
| LMArena Multi-Turn | 1222 | — |
| LiveBench Language | 23.3% | — |
Frequently asked questions
Is Qwen2.5-Coder-32B better than Qwen3 14B?
Qwen3 14B is the stronger model overall, scoring 35.0 to 32.9 on the Noometry Index.
Which is cheaper, Qwen2.5-Coder-32B or Qwen3 14B?
Qwen3 14B 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-Coder-32B or Qwen3 14B better for coding?
Qwen3 14B scores higher on coding benchmarks: 36.7 versus 22.4 in the Noometry coding category.
Which has the bigger context window?
Qwen3 14B does, with 131K tokens against 33K.
How many benchmarks do Qwen2.5-Coder-32B and Qwen3 14B share?
1 benchmark has published results for both models. Qwen2.5-Coder-32B has 31 scored results on Noometry and Qwen3 14B has 12.