Model comparison
DeepSeek-R1 vs Qwen3-Coder 480B-A35B Instruct
DeepSeek-R1 is the stronger model overall, scoring 42.3 to 38.1 on the Noometry Index.
Last verified . 21 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- They share 21 benchmarks with published results for both. DeepSeek-R1 scores higher in 8 categories and Qwen3-Coder 480B-A35B Instruct in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where DeepSeek-R1 leads 46.3 to 35.5.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 69.4% for DeepSeek-R1 and 49.5% for Qwen3-Coder 480B-A35B Instruct.
- DeepSeek-R1 is cheaper at $0.50 / $2.15 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.
- Qwen3-Coder 480B-A35B Instruct has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-R1 | Qwen3-Coder 480B-A35B Instruct | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 42.3 | 38.1 |
| Released | 2025-01-20 | 2025-04 |
| Weights | Proprietary | Open |
| Context window | 164K | 262K |
| Max output | 64K | 66K |
| Input $ / M tokens | $0.50 | $1.50 |
| Output $ / M tokens | $2.15 | $7.50 |
| Results tracked | 52 | 25 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-R1 leads
DeepSeek-R1: 46.3 (#68), Qwen3-Coder 480B-A35B Instruct: 35.5 (#223)
| Benchmark | DeepSeek-R1 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| WeirdML | 41.6% | 41.2% |
| LMArena Coding | 1427 | 1412 |
| ALE-Bench | 804.12 | 461.45 |
| AlgoTune | 1.7 | 1.44 |
| SWE-bench Verified (bash only) | — | 55.4% |
| Aider Polyglot | 71.4% | — |
| LMArena WebDev | — | 1275 |
| SciCode | 35.7% | — |
| GSO | — | 4.9% |
| LiveBench Coding | 66.7% | — |
Agentic & Tool Use DeepSeek-R1 leads
DeepSeek-R1: 30.7 (#75), Qwen3-Coder 480B-A35B Instruct: 23.9 (#123)
| Benchmark | DeepSeek-R1 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| Terminal-Bench | — | 27.2% |
| DeepResearch Bench | 35.1% | — |
| BALROG | 34.9% | — |
| METR Time Horizons | 53.8% | — |
Reasoning Qwen3-Coder 480B-A35B Instruct leads
DeepSeek-R1: 18.6 (#278), Qwen3-Coder 480B-A35B Instruct: 25.5 (#149)
| Benchmark | DeepSeek-R1 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| Kagi LLM Benchmark | 69.4% | 49.5% |
| LMArena Hard Prompts | 1416 | 1372 |
| ARC-AGI-2 | 1.3% | — |
| SimpleBench | 40.8% | — |
| ARC-AGI-1 | 21.2% | — |
| CritPt | 1.1% | — |
| LiveBench Reasoning | 83.2% | — |
| LiveBench Data Analysis | 69.8% | — |
| Epoch Capabilities Index | 141.29 | — |
| ForecastBench | 60 | — |
| LiveBench | 71.6% | — |
Math DeepSeek-R1 leads
DeepSeek-R1: 43.8 (#79), Qwen3-Coder 480B-A35B Instruct: 37.6 (#150)
| Benchmark | DeepSeek-R1 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Math | 1400 | 1365 |
| OTIS Mock AIME 2024-2025 | 66.4% | — |
| Omni-MATH | 42.4% | — |
| LiveBench Math | 80.7% | — |
| MATH Level 5 | 96.6% | — |
Knowledge DeepSeek-R1 leads
DeepSeek-R1: 44.5 (#87), Qwen3-Coder 480B-A35B Instruct: 37.0 (#162)
| Benchmark | DeepSeek-R1 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Expert | 1394 | 1338 |
| GPQA Diamond | 76.3% | — |
| MMLU-Pro | 79.3% | — |
| Confabulations | 12.7% | — |
| Vectara Hallucination Rate | 11.3% | — |
| GPQA (HELM) | 66.6% | — |
Multilingual DeepSeek-R1 leads
DeepSeek-R1: 52.4 (#85), Qwen3-Coder 480B-A35B Instruct: 47.7 (#148)
| Benchmark | DeepSeek-R1 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Non-English | 1412 | 1346 |
| LMArena Chinese | 1442 | 1357 |
| LMArena French | 1417 | 1398 |
| LMArena German | 1404 | 1325 |
| LMArena Japanese | 1391 | 1310 |
| LMArena Korean | 1360 | 1305 |
| LMArena Russian | 1423 | 1366 |
| LMArena Spanish | 1411 | 1360 |
Instruction Following Too close to call
DeepSeek-R1: 72.0 (#143), Qwen3-Coder 480B-A35B Instruct: 71.6 (#147)
| Benchmark | DeepSeek-R1 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Instruction Following | 1382 | 1355 |
| LiveBench Instruction Following | 80.5% | — |
| IFEval | 78.4% | — |
Long Context DeepSeek-R1 leads
DeepSeek-R1: 45.4 (#36), Qwen3-Coder 480B-A35B Instruct: 42.0 (#131)
| Benchmark | DeepSeek-R1 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Longer Query | 1391 | 1378 |
| Fiction.LiveBench | 75% | — |
Writing & Preference DeepSeek-R1 leads
DeepSeek-R1: 61.4 (#88), Qwen3-Coder 480B-A35B Instruct: 55.3 (#147)
| Benchmark | DeepSeek-R1 | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Text | 1428 | 1357 |
| LMArena Creative Writing | 1405 | 1333 |
| LMArena Multi-Turn | 1405 | 1365 |
| Short-Story Creative Writing | 83% | — |
| EQ-Bench Creative Writing | 1500 | — |
| WildBench | 82.8% | — |
| LiveBench Language | 48.5% | — |
Frequently asked questions
Is DeepSeek-R1 better than Qwen3-Coder 480B-A35B Instruct?
DeepSeek-R1 is the stronger model overall, scoring 42.3 to 38.1 on the Noometry Index.
Which is cheaper, DeepSeek-R1 or Qwen3-Coder 480B-A35B Instruct?
DeepSeek-R1 is cheaper. It lists at $0.50 per million input tokens and $2.15 per million output tokens; Qwen3-Coder 480B-A35B Instruct lists at $1.50 and $7.50.
Is DeepSeek-R1 or Qwen3-Coder 480B-A35B Instruct better for coding?
DeepSeek-R1 scores higher on coding benchmarks: 46.3 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-R1 and Qwen3-Coder 480B-A35B Instruct share?
21 benchmarks have published results for both models. DeepSeek-R1 has 52 scored results on Noometry and Qwen3-Coder 480B-A35B Instruct has 25.