Model comparison
DeepSeek-V3.1 vs Qwen3-Coder 480B-A35B Instruct
DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 38.1 on the Noometry Index.
Last verified . 19 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- They share 19 benchmarks with published results for both. DeepSeek-V3.1 scores higher in 7 categories and Qwen3-Coder 480B-A35B Instruct in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where DeepSeek-V3.1 leads 43.7 to 37.0.
- DeepSeek-V3.1 is cheaper at $0.25 / $0.95 per million input/output tokens, against $1.50 / $7.50 for Qwen3-Coder 480B-A35B Instruct.
- Qwen3-Coder 480B-A35B Instruct accepts more context: 262K tokens versus 164K.
Side by side
| DeepSeek-V3.1 | Qwen3-Coder 480B-A35B Instruct | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 42.8 | 38.1 |
| Released | 2025-08-21 | 2025-04 |
| Weights | Open | Open |
| Context window | 164K | 262K |
| Max output | 8K | 66K |
| Input $ / M tokens | $0.25 | $1.50 |
| Output $ / M tokens | $0.95 | $7.50 |
| Results tracked | 27 | 25 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.1 leads
DeepSeek-V3.1: 40.3 (#144), Qwen3-Coder 480B-A35B Instruct: 35.5 (#223)
| Benchmark | DeepSeek-V3.1 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| WeirdML | 38.4% | 41.2% |
| LMArena Coding | 1417 | 1412 |
| SWE-bench Verified (bash only) | — | 55.4% |
| LMArena WebDev | — | 1275 |
| GSO | — | 4.9% |
| ALE-Bench | — | 461.45 |
| AlgoTune | — | 1.44 |
Agentic & Tool Use Not comparable
DeepSeek-V3.1: —, Qwen3-Coder 480B-A35B Instruct: 23.9 (#123)
| Benchmark | DeepSeek-V3.1 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| Terminal-Bench | — | 27.2% |
Reasoning DeepSeek-V3.1 leads
DeepSeek-V3.1: 27.9 (#110), Qwen3-Coder 480B-A35B Instruct: 25.5 (#149)
| Benchmark | DeepSeek-V3.1 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| Kagi LLM Benchmark | 53.2% | 49.5% |
| LMArena Hard Prompts | 1417 | 1372 |
| SimpleBench | 40% | — |
| DTBench | 82.7% | — |
| LMCA | 24.3% | — |
| Epoch Capabilities Index | 139.92 | — |
| ForecastBench | 58 | — |
Math DeepSeek-V3.1 leads
DeepSeek-V3.1: 38.9 (#122), Qwen3-Coder 480B-A35B Instruct: 37.6 (#150)
| Benchmark | DeepSeek-V3.1 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Math | 1420 | 1365 |
Knowledge DeepSeek-V3.1 leads
DeepSeek-V3.1: 43.7 (#90), Qwen3-Coder 480B-A35B Instruct: 37.0 (#162)
| Benchmark | DeepSeek-V3.1 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Expert | 1405 | 1338 |
| Vectara Hallucination Rate | 5.5% | — |
Multilingual DeepSeek-V3.1 leads
DeepSeek-V3.1: 51.6 (#106), Qwen3-Coder 480B-A35B Instruct: 47.7 (#148)
| Benchmark | DeepSeek-V3.1 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Non-English | 1400 | 1346 |
| LMArena Chinese | 1469 | 1357 |
| LMArena French | 1447 | 1398 |
| LMArena German | 1411 | 1325 |
| LMArena Japanese | 1378 | 1310 |
| LMArena Korean | 1337 | 1305 |
| LMArena Russian | 1405 | 1366 |
| LMArena Spanish | 1431 | 1360 |
Instruction Following DeepSeek-V3.1 leads
DeepSeek-V3.1: 73.9 (#110), Qwen3-Coder 480B-A35B Instruct: 71.6 (#147)
| Benchmark | DeepSeek-V3.1 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Instruction Following | 1400 | 1355 |
Long Context Qwen3-Coder 480B-A35B Instruct leads
DeepSeek-V3.1: 36.3 (#232), Qwen3-Coder 480B-A35B Instruct: 42.0 (#131)
| Benchmark | DeepSeek-V3.1 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Longer Query | 1422 | 1378 |
| Fiction.LiveBench | 52.8% | — |
Writing & Preference DeepSeek-V3.1 leads
DeepSeek-V3.1: 60.3 (#98), Qwen3-Coder 480B-A35B Instruct: 55.3 (#147)
| Benchmark | DeepSeek-V3.1 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Text | 1420 | 1357 |
| LMArena Creative Writing | 1401 | 1333 |
| LMArena Multi-Turn | 1408 | 1365 |
| EQ-Bench Creative Writing | 1436 | — |
Frequently asked questions
Is DeepSeek-V3.1 better than Qwen3-Coder 480B-A35B Instruct?
DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 38.1 on the Noometry Index.
Which is cheaper, DeepSeek-V3.1 or Qwen3-Coder 480B-A35B Instruct?
DeepSeek-V3.1 is cheaper. It lists at $0.25 per million input tokens and $0.95 per million output tokens; Qwen3-Coder 480B-A35B Instruct lists at $1.50 and $7.50.
Is DeepSeek-V3.1 or Qwen3-Coder 480B-A35B Instruct better for coding?
DeepSeek-V3.1 scores higher on coding benchmarks: 40.3 versus 35.5 in the Noometry coding category.
Which has the bigger context window?
Qwen3-Coder 480B-A35B Instruct does, with 262K tokens against 164K.
How many benchmarks do DeepSeek-V3.1 and Qwen3-Coder 480B-A35B Instruct share?
19 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and Qwen3-Coder 480B-A35B Instruct has 25.