Model comparison
DeepSeek-V3 vs Qwen Plus
DeepSeek-V3 is the stronger model overall, scoring 39.2 to 36.7 on the Noometry Index.
Last verified . 20 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- They share 20 benchmarks with published results for both. DeepSeek-V3 scores higher in 6 categories and Qwen Plus in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where DeepSeek-V3 leads 37.5 to 27.4.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 37.8% for DeepSeek-V3 and 17.8% for Qwen Plus.
- DeepSeek-V3 is cheaper at $0.24 / $0.90 per million input/output tokens, against $0.40 / $1.20 for Qwen Plus.
- Qwen Plus accepts more context: 1M tokens versus 164K.
- DeepSeek-V3 has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V3 | Qwen Plus | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 39.2 | 36.7 |
| Released | 2024-12-26 | 2024-01-25 |
| Weights | Open | Proprietary |
| Context window | 164K | 1M |
| Max output | 164K | 33K |
| Input $ / M tokens | $0.24 | $0.40 |
| Output $ / M tokens | $0.90 | $1.20 |
| Results tracked | 60 | 20 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3 leads
DeepSeek-V3: 41.9 (#99), Qwen Plus: 38.3 (#163)
| Benchmark | DeepSeek-V3 | Qwen Plus |
|---|---|---|
| LMArena Coding | 1368 | 1328 |
| Aider Polyglot | 55.1% | — |
| SciCode | 35.8% | — |
| WeirdML | 36.1% | — |
| BigCodeBench Instruct | 50% | — |
| LiveBench Coding | 70.9% | — |
| BigCodeBench Complete | 62.2% | — |
| HumanEval+ | 86.6% | — |
| MBPP+ | 73% | — |
Agentic & Tool Use Not comparable
DeepSeek-V3: —, Qwen Plus: —
| Benchmark | DeepSeek-V3 | Qwen Plus |
|---|---|---|
| METR Time Horizons | 49.6% | — |
Reasoning Qwen Plus leads
DeepSeek-V3: 20.0 (#226), Qwen Plus: 27.6 (#101)
| Benchmark | DeepSeek-V3 | Qwen Plus |
|---|---|---|
| Kagi LLM Benchmark | 52.3% | 63.3% |
| LMArena Hard Prompts | 1365 | 1317 |
| DTBench | 64.8% | 81.1% |
| LMCA | 15.5% | 24% |
| SimpleBench | 27.2% | — |
| CritPt | 0% | — |
| LiveBench Reasoning | 65.8% | — |
| LiveBench Data Analysis | 60.9% | — |
| BIG-Bench Hard | 87.5% | — |
| Epoch Capabilities Index | 135.95 | — |
| ForecastBench | 59.1 | — |
| HellaSwag | 88.9% | — |
| LiveBench | 66.9% | — |
| PIQA | 84.7% | — |
| WinoGrande | 85.2% | — |
Math DeepSeek-V3 leads
DeepSeek-V3: 30.4 (#208), Qwen Plus: 22.0 (#266)
| Benchmark | DeepSeek-V3 | Qwen Plus |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 37.8% | 17.8% |
| LMArena Math | 1373 | 1326 |
| MATH Level 5 | 75.5% | 65.3% |
| FrontierMath (Feb 2025 set) | 1.7% | 1.7% |
| Omni-MATH | 40.3% | — |
| LiveBench Math | 73.5% | — |
Knowledge DeepSeek-V3 leads
DeepSeek-V3: 37.5 (#147), Qwen Plus: 27.4 (#245)
| Benchmark | DeepSeek-V3 | Qwen Plus |
|---|---|---|
| GPQA Diamond | 67.6% | 48.1% |
| LMArena Expert | 1352 | 1328 |
| MMLU-Pro | 72.3% | — |
| Confabulations | 26.1% | — |
| Vectara Hallucination Rate | 6.1% | — |
| GPQA (HELM) | 53.8% | — |
| ARC (AI2) Challenge | 95.3% | — |
| MMLU | 87.2% | — |
| TriviaQA | 82.9% | — |
Multilingual DeepSeek-V3 leads
DeepSeek-V3: 48.8 (#138), Qwen Plus: 45.3 (#170)
| Benchmark | DeepSeek-V3 | Qwen Plus |
|---|---|---|
| LMArena Non-English | 1358 | 1310 |
| LMArena Chinese | 1390 | 1347 |
| LMArena Japanese | 1333 | 1251 |
| LMArena Russian | 1372 | 1323 |
| LMArena French | 1386 | — |
| LMArena German | 1374 | — |
| LMArena Korean | 1321 | — |
| LMArena Spanish | 1358 | — |
Instruction Following DeepSeek-V3 leads
DeepSeek-V3: 73.0 (#125), Qwen Plus: 69.0 (#176)
| Benchmark | DeepSeek-V3 | Qwen Plus |
|---|---|---|
| LMArena Instruction Following | 1345 | 1303 |
| LiveBench Instruction Following | 81.5% | — |
| IFEval | 83.2% | — |
Long Context Qwen Plus leads
DeepSeek-V3: 34.0 (#248), Qwen Plus: 40.3 (#153)
| Benchmark | DeepSeek-V3 | Qwen Plus |
|---|---|---|
| LMArena Longer Query | 1353 | 1325 |
| Fiction.LiveBench | 50% | — |
Writing & Preference DeepSeek-V3 leads
DeepSeek-V3: 57.6 (#124), Qwen Plus: 52.4 (#171)
| Benchmark | DeepSeek-V3 | Qwen Plus |
|---|---|---|
| LMArena Text | 1375 | 1326 |
| LMArena Creative Writing | 1364 | 1293 |
| LMArena Multi-Turn | 1389 | 1336 |
| Short-Story Creative Writing | 77% | — |
| EQ-Bench Creative Writing | 1472 | — |
| WildBench | 83% | — |
| LiveBench Language | 49.1% | — |
Frequently asked questions
Is DeepSeek-V3 better than Qwen Plus?
DeepSeek-V3 is the stronger model overall, scoring 39.2 to 36.7 on the Noometry Index.
Which is cheaper, DeepSeek-V3 or Qwen Plus?
DeepSeek-V3 is cheaper. It lists at $0.24 per million input tokens and $0.90 per million output tokens; Qwen Plus lists at $0.40 and $1.20.
Is DeepSeek-V3 or Qwen Plus better for coding?
DeepSeek-V3 scores higher on coding benchmarks: 41.9 versus 38.3 in the Noometry coding category.
Which has the bigger context window?
Qwen Plus does, with 1M tokens against 164K.
How many benchmarks do DeepSeek-V3 and Qwen Plus share?
20 benchmarks have published results for both models. DeepSeek-V3 has 60 scored results on Noometry and Qwen Plus has 20.