Alibaba (Qwen), open weights
Qwen2.5-Coder-32B
Qwen2.5-Coder-32B by Alibaba (Qwen) ranks 245th of 354 ranked models on the Noometry Index as of October 2026, with a score of 33.4. Its strongest category is knowledge, where it ranks 203rd. API pricing starts at $0.66 per million input tokens and $1 per million output tokens, with a 33K-token context window.
Last verified
Specifications
- Noometry rank
- #245 of 354
- Index score
- 33.4
- Evidence
- Confirmed 31 results
- Provider
Alibaba (Qwen)- Released
- September 18, 2024
- Weights
- Open weights
- Reasoning
- Unknown
- Context window
- 33K
- Max output
- 29K
- Input price
- $0.66 / M
- Output price
- $1 / M
- Blended price
- $0.74 / M
- Output speed
- Not measured
- Value
- #106 of 219
- Knowledge cutoff
- Unknown
- Input
- text
- Hugging Face
- Qwen/Qwen2.5-Coder-32B-Instruct
Category scores
Each category score combines every public result we have in that category.
- Coding 22.6
- Reasoning 21.2
- Math 33.3
- Knowledge 33.4
- Multilingual 37.8
- Instruction Following 61.4
- Long Context 38.0
- Writing & Preference 41.6
| Category | Score | Rank | Results |
|---|---|---|---|
| Coding | 22.6 | #333 | 6 |
| Reasoning | 21.2 | #225 | 3 |
| Math | 33.3 | #204 | 2 |
| Knowledge | 33.4 | #203 | 1 |
| Multilingual | 37.8 | #235 | 1 |
| Instruction Following | 61.4 | #245 | 2 |
| Long Context | 38.0 | #208 | 1 |
| Writing & Preference | 41.6 | #240 | 4 |
Strengths and weaknesses
Categories where Qwen2.5-Coder-32B places highest and lowest among the models ranked in each, with its score against that category's median.
Strongest categories
Weakest categories
| Category | Score | vs median | Rank |
|---|---|---|---|
| Coding | 22.6 | −16.1 | #333 of 340, top 98% |
| Instruction Following | 61.4 | −9.9 | #245 of 305, top 81% |
| Multilingual | 37.8 | −9.6 | #235 of 297, top 80% |
Closest competitors
The models ranked just above and below Qwen2.5-Coder-32B. When scores are this close, price and speed are often the better way to choose.
| Model | Rank | Score | Blended $/M | Speed | |
|---|---|---|---|---|---|
| GPT-5 Nano | #241 | 33.5 | $0.14 | 4 | Compare |
| Mercury 2.5 | #242 | 33.5 | $0.0675 | — | Compare |
| Mistral Small | #243 | 33.4 | $0.26 | 120 | Compare |
| Nova 2.0 Pro Preview | #244 | 33.4 | — | — | Compare |
| Gemini 1.5 Flash (May 2024) | #246 | 33.2 | — | — | Compare |
| Granite 3.1 2b Instruct | #247 | 33.2 | — | — | Compare |
| Gemma 2 2b IT | #248 | 33.1 | — | — | Compare |
| Wizardlm 70b | #249 | 33.0 | — | — | Compare |
Sponsored placements are available on pages like this one. Advertise on Noometry
Benchmark results
Every published result we track, with its source. Bold rows are the ones used for ranking; where several exist we prefer independent runs over self-reported numbers.
Coding
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| SWE-bench Verified (bash only) | 9% | #39 of 39, top 100% | SWE-bench | 2025-08-03 | |
| Aider Polyglot | 16.4% | #37 of 44, top 85% | Epoch AI | ||
| BigCodeBench Instruct | 49% | #4 of 64, top 7% | BigCodeBench | 2024-09-19 | |
| LiveBench Coding | 56.9% | #14 of 39, top 36% | Epoch AI | ||
| LMArena Coding | 1276 | #212 of 294, top 73% | LMArena | 2026-10-08 | |
| BigCodeBench Complete | 58% | #10 of 66, top 16% | BigCodeBench | 2024-09-19 | |
| HumanEval+ | 87.2% | #4 of 45, top 9% | EvalPlus | ||
| MBPP+ | 77% | #3 of 38, top 8% | EvalPlus |
Reasoning
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LiveBench Reasoning | 42.1% | #26 of 39, top 67% | Epoch AI | ||
| LMArena Hard Prompts | 1251 | #219 of 297, top 74% | LMArena | 2026-10-08 | |
| LiveBench Data Analysis | 49.9% | #24 of 39, top 62% | Epoch AI | ||
| Epoch Capabilities Index | 119.49 | #170 of 213, top 80% | Epoch AI | 2024-09-18 | |
| HellaSwag | 83% | #11 of 29, top 38% | Epoch AI | ||
| LiveBench | 46.2% | #24 of 39, top 62% | Epoch AI | ||
| WinoGrande | 80.8% | #14 of 43, top 33% | Epoch AI |
Math
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LiveBench Math | 46.6% | #21 of 39, top 54% | Epoch AI | ||
| LMArena Math | 1251 | #213 of 285, top 75% | LMArena | 2026-10-08 | |
| GSM8K | 91.1% | Epoch AI | |||
| GSM8K | 93% | #2 of 38, top 6% | Epoch AI |
Knowledge
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Expert | 1221 | #214 of 273, top 79% | LMArena | 2026-10-08 | |
| ARC (AI2) Challenge | 70.5% | #18 of 39, top 47% | Epoch AI | ||
| MMLU | 79.1% | #22 of 81, top 28% | Epoch AI |
Multilingual
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Non-English | 1205 | #235 of 297, top 80% | LMArena | 2026-10-08 | |
| LMArena Chinese | 1222 | #222 of 285, top 78% | LMArena | 2026-10-08 | |
| LMArena Russian | 1228 | #222 of 283, top 79% | LMArena | 2026-10-08 |
Instruction Following
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LiveBench Instruction Following | 58.7% | #28 of 39, top 72% | Epoch AI | ||
| LMArena Instruction Following | 1223 | #228 of 298, top 77% | LMArena | 2026-10-08 |
Long Context
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Longer Query | 1251 | #221 of 291, top 76% | LMArena | 2026-10-08 |
Writing & Preference
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Text | 1230 | #230 of 297, top 78% | LMArena | 2026-10-08 | |
| LMArena Creative Writing | 1174 | #243 of 295, top 83% | LMArena | 2026-10-08 | |
| LMArena Multi-Turn | 1222 | #231 of 295, top 79% | LMArena | 2026-10-08 | |
| LiveBench Language | 23.3% | #34 of 39, top 88% | Epoch AI |
API pricing by provider
| Route | Input $/M | Output $/M | Cached input $/M | Checked |
|---|---|---|---|---|
| openrouter | $0.66 | $1 | — | 2026-10-10 |
Compare Qwen2.5-Coder-32B
- Qwen2.5-Coder-32B vs Nova 2.0 Pro Preview
- Qwen2.5-Coder-32B vs Gemini 1.5 Flash (May 2024)
- Qwen2.5-Coder-32B vs Mistral Small
- Qwen2.5-Coder-32B vs Granite 3.1 2b Instruct
- Qwen2.5-Coder-32B vs Mercury 2.5
- Qwen2.5-Coder-32B vs Gemma 2 2b IT
- Qwen2.5-Coder-32B vs GPT-6 Astra
- Qwen2.5-Coder-32B vs Claude Fable 5.1
- Qwen2.5-Coder-32B vs Gemini 3.8 Flash
- Qwen2.5-Coder-32B vs Kimi K3
- Qwen2.5-Coder-32B vs Grok 4.6
- Qwen2.5-Coder-32B vs GLM-5.3
- Qwen2.5-Coder-32B vs Muse Spark 1.3
- Qwen2.5-Coder-32B vs DeepSeek V4 Pro
Other Alibaba (Qwen) models
- Qwen3.8 Max56.8
- Qwen3.7 Max51.5
- Qwen3.6 Max Preview51.5
- Qwen3.6 Plus47.5
- Qwen3.5 397B-A17B46.0
- Qwen3.8 27B46.0
- Qwen3.5 Max Preview45.3
- Qwen3.7 Plus45.3
Frequently asked questions
How good is Qwen2.5-Coder-32B?
Qwen2.5-Coder-32B by Alibaba (Qwen) ranks 245th of 354 ranked models on the Noometry Index as of October 2026, with a score of 33.4. Its strongest category is knowledge, where it ranks 203rd. API pricing starts at $0.66 per million input tokens and $1 per million output tokens, with a 33K-token context window.
How much does Qwen2.5-Coder-32B cost?
Qwen2.5-Coder-32B costs $0.66 per million input tokens and $1 per million output tokens on openrouter.
What is Qwen2.5-Coder-32B's context window?
Qwen2.5-Coder-32B accepts up to 33K tokens of input and can write up to 29K tokens in one response.
Is Qwen2.5-Coder-32B open source?
Yes. Qwen2.5-Coder-32B's weights are downloadable from Hugging Face (Qwen/Qwen2.5-Coder-32B-Instruct); check the license for commercial terms.
What are Qwen2.5-Coder-32B's strengths and weaknesses?
Relative to other ranked models, Qwen2.5-Coder-32B places best in math, reasoning, knowledge and lowest in coding, instruction following, multilingual.
What is Qwen2.5-Coder-32B best at?
Its best category is knowledge, where it ranks 203rd on Noometry.