Alibaba (Qwen), open weights
Qwen3-Coder 480B-A35B Instruct
Qwen3-Coder 480B-A35B Instruct by Alibaba (Qwen) ranks 190th of 354 ranked models on the Noometry Index as of October 2026, with a score of 38.1. Its strongest category is agentic & tool use, where it ranks 123rd. API pricing starts at $1.50 per million input tokens and $7.50 per million output tokens, with a 262K-token context window.
Last verified
Specifications
- Noometry rank
- #190 of 354
- Index score
- 38.1
- Evidence
- Confirmed 25 results
- Provider
Alibaba (Qwen)- Released
- April 1, 2025
- Weights
- Open weights
- Reasoning
- No
- Context window
- 262K
- Max output
- 66K
- Input price
- $1.50 / M
- Output price
- $7.50 / M
- Blended price
- $3 / M
- Output speed
- 67 tokens/s Kagi
- Value
- #174 of 219
- Knowledge cutoff
- April 2025
- Input
- text
- Hugging Face
- Qwen/Qwen3-Coder-480B-A35B-Instruct
Category scores
Each category score combines every public result we have in that category.
- Coding 35.5
- Agentic & Tool Use 23.9
- Reasoning 25.5
- Math 37.6
- Knowledge 37.0
- Multilingual 47.7
- Instruction Following 71.6
- Long Context 42.0
- Writing & Preference 55.3
| Category | Score | Rank | Results |
|---|---|---|---|
| Coding | 35.5 | #223 | 5 |
| Agentic & Tool Use | 23.9 | #123 | 1 |
| Reasoning | 25.5 | #149 | 2 |
| Math | 37.6 | #150 | 1 |
| Knowledge | 37.0 | #162 | 1 |
| Multilingual | 47.7 | #148 | 1 |
| Instruction Following | 71.6 | #147 | 1 |
| Long Context | 42.0 | #131 | 1 |
| Writing & Preference | 55.3 | #147 | 3 |
Strengths and weaknesses
Categories where Qwen3-Coder 480B-A35B Instruct places highest and lowest among the models ranked in each, with its score against that category's median.
Strongest categories
| Category | Score | vs median | Rank |
|---|---|---|---|
| Reasoning | 25.5 | +1.9 | #149 of 350, top 43% |
| Long Context | 42.0 | +1.1 | #131 of 296, top 45% |
| Math | 37.6 | +1.1 | #150 of 327, top 46% |
Weakest categories
| Category | Score | vs median | Rank |
|---|---|---|---|
| Agentic & Tool Use | 23.9 | −6.4 | #123 of 154, top 80% |
| Coding | 35.5 | −3.2 | #223 of 340, top 66% |
| Knowledge | 37.0 | −0.3 | #162 of 314, top 52% |
Closest competitors
The models ranked just above and below Qwen3-Coder 480B-A35B Instruct. When scores are this close, price and speed are often the better way to choose.
| Model | Rank | Score | Blended $/M | Speed | |
|---|---|---|---|---|---|
| GPT-5.1-Codex | #186 | 38.6 | $3.44 | — | Compare |
| Sonar | #187 | 38.5 | $1 | — | Compare |
| MiniMax-M2.5 | #188 | 38.3 | $0.52 | 49 | Compare |
| Nova Premier 1.0 | #189 | 38.3 | $5 | 9 | Compare |
| Olmo 3.1 32b Think | #191 | 37.9 | — | — | Compare |
| GPT-5-Codex | #192 | 37.9 | $3.44 | 95 | Compare |
| Hunyuan Standard 2025 02 10 | #193 | 37.9 | — | — | Compare |
| Gemini 2.0 Flash-Lite | #194 | 37.8 | — | — | 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) | 55.4% | #24 of 39, top 62% | SWE-bench | 2025-08-02 | |
| LMArena WebDev | 1275 | #98 of 113, top 87% | LMArena | 2026-10-08 | |
| GSO | 4.9% | #23 of 31, top 75% | Epoch AI | ||
| WeirdML | 41.2% | #73 of 119, top 62% | Epoch AI | ||
| LMArena Coding | 1412 | #127 of 294, top 44% | LMArena | 2026-10-08 | |
| ALE-Bench | 461.45 | #87 of 105, top 83% | Epoch AI | ||
| AlgoTune | 1.44 | #13 of 18, top 73% | Epoch AI |
Agentic & Tool Use
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| Terminal-Bench | 27.2% | #34 of 41, top 83% | Epoch AI |
Reasoning
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| Kagi LLM Benchmark | 49.5% | #65 of 99, top 66% | Kagi LLM Benchmark | ||
| LMArena Hard Prompts | 1372 | #146 of 297, top 50% | LMArena | 2026-10-08 |
Math
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Math | 1365 | #154 of 285, top 55% | LMArena | 2026-10-08 |
Knowledge
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Expert | 1338 | #160 of 273, top 59% | LMArena | 2026-10-08 |
Multilingual
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Non-English | 1346 | #148 of 297, top 50% | LMArena | 2026-10-08 | |
| LMArena Chinese | 1357 | #164 of 285, top 58% | LMArena | 2026-10-08 | |
| LMArena French | 1398 | #119 of 223, top 54% | LMArena | 2026-10-08 | |
| LMArena German | 1325 | #144 of 231, top 63% | LMArena | 2026-10-08 | |
| LMArena Japanese | 1310 | #116 of 211, top 55% | LMArena | 2026-10-08 | |
| LMArena Korean | 1305 | #129 of 213, top 61% | LMArena | 2026-10-08 | |
| LMArena Russian | 1366 | #138 of 283, top 49% | LMArena | 2026-10-08 | |
| LMArena Spanish | 1360 | #136 of 226, top 61% | LMArena | 2026-10-08 |
Instruction Following
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Instruction Following | 1355 | #141 of 298, top 48% | LMArena | 2026-10-08 |
Long Context
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Longer Query | 1378 | #134 of 291, top 47% | LMArena | 2026-10-08 |
Writing & Preference
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Text | 1357 | #153 of 297, top 52% | LMArena | 2026-10-08 | |
| LMArena Creative Writing | 1333 | #142 of 295, top 49% | LMArena | 2026-10-08 | |
| LMArena Multi-Turn | 1365 | #143 of 295, top 49% | LMArena | 2026-10-08 |
API pricing by provider
| Route | Input $/M | Output $/M | Cached input $/M | Checked |
|---|---|---|---|---|
| alibaba | $1.50 | $7.50 | — | 2026-10-10 |
| bedrock | $0.45 | $1.80 | — | 2026-10-10 |
| deepinfra | $0.30 | $1 | $0.10 | 2026-10-10 |
| openrouter | $0.30 | $1 | $0.10 | 2026-10-10 |
| together | $2 | $2 | — | 2026-10-10 |
Compare Qwen3-Coder 480B-A35B Instruct
- Qwen3-Coder 480B-A35B Instruct vs Nova Premier 1.0
- Qwen3-Coder 480B-A35B Instruct vs Olmo 3.1 32b Think
- Qwen3-Coder 480B-A35B Instruct vs MiniMax-M2.5
- Qwen3-Coder 480B-A35B Instruct vs GPT-5-Codex
- Qwen3-Coder 480B-A35B Instruct vs Sonar
- Qwen3-Coder 480B-A35B Instruct vs Hunyuan Standard 2025 02 10
- Qwen3-Coder 480B-A35B Instruct vs GPT-6 Astra
- Qwen3-Coder 480B-A35B Instruct vs Claude Fable 5.1
- Qwen3-Coder 480B-A35B Instruct vs Gemini 3.8 Flash
- Qwen3-Coder 480B-A35B Instruct vs Kimi K3
- Qwen3-Coder 480B-A35B Instruct vs Grok 4.6
- Qwen3-Coder 480B-A35B Instruct vs GLM-5.3
- Qwen3-Coder 480B-A35B Instruct vs Muse Spark 1.3
- Qwen3-Coder 480B-A35B Instruct 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 Qwen3-Coder 480B-A35B Instruct?
Qwen3-Coder 480B-A35B Instruct by Alibaba (Qwen) ranks 190th of 354 ranked models on the Noometry Index as of October 2026, with a score of 38.1. Its strongest category is agentic & tool use, where it ranks 123rd. API pricing starts at $1.50 per million input tokens and $7.50 per million output tokens, with a 262K-token context window.
How much does Qwen3-Coder 480B-A35B Instruct cost?
Qwen3-Coder 480B-A35B Instruct costs $1.50 per million input tokens and $7.50 per million output tokens on Alibaba (Qwen)'s own API.
What is Qwen3-Coder 480B-A35B Instruct's context window?
Qwen3-Coder 480B-A35B Instruct accepts up to 262K tokens of input and can write up to 66K tokens in one response.
Is Qwen3-Coder 480B-A35B Instruct open source?
Yes. Qwen3-Coder 480B-A35B Instruct's weights are downloadable from Hugging Face (Qwen/Qwen3-Coder-480B-A35B-Instruct); check the license for commercial terms.
How fast is Qwen3-Coder 480B-A35B Instruct?
Qwen3-Coder 480B-A35B Instruct generated about 67 output tokens per second in the Kagi LLM Benchmark's timed runs. Speed varies by provider, load and reasoning effort.
What are Qwen3-Coder 480B-A35B Instruct's strengths and weaknesses?
Relative to other ranked models, Qwen3-Coder 480B-A35B Instruct places best in reasoning, long context, math and lowest in agentic & tool use, coding, knowledge.
What is Qwen3-Coder 480B-A35B Instruct best at?
Its best category is agentic & tool use, where it ranks 123rd on Noometry.