Model comparison
DeepSeek-V3 vs Qwen3.8 27B
Qwen3.8 27B is the stronger model overall, scoring 46.0 to 39.5 on the Noometry Index. DeepSeek-V3 costs 2.8× less per token, which makes it the better buy when Qwen3.8 27B's lead doesn't matter for your workload.
Last verified . 23 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- They share 23 benchmarks with published results for both. DeepSeek-V3 scores higher in 0 categories and Qwen3.8 27B in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3.8 27B leads 41.0 to 20.5.
- The biggest single-benchmark swing is LMCA: 15.5% for DeepSeek-V3 and 41.4% for Qwen3.8 27B.
- DeepSeek-V3 is cheaper at $0.24 / $0.90 per million input/output tokens, against $0.99 / $1.49 for Qwen3.8 27B.
- Qwen3.8 27B accepts more context: 262K tokens versus 164K.
Side by side
| DeepSeek-V3 | Qwen3.8 27B | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 39.5 | 46.0 |
| Released | 2024-12-26 | 2026-08-14 |
| Weights | Open | Open |
| Context window | 164K | 262K |
| Max output | 164K | 33K |
| Input $ / M tokens | $0.24 | $0.99 |
| Output $ / M tokens | $0.90 | $1.49 |
| Results tracked | 60 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.8 27B leads
DeepSeek-V3: 42.3 (#106), Qwen3.8 27B: 50.5 (#44)
| Benchmark | DeepSeek-V3 | Qwen3.8 27B |
|---|---|---|
| SciCode | 35.8% | 46.6% |
| LMArena Coding | 1368 | 1482 |
| Aider Polyglot | 55.1% | — |
| LMArena WebDev | — | 1593 |
| 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: —, Qwen3.8 27B: 32.9 (#57)
| Benchmark | DeepSeek-V3 | Qwen3.8 27B |
|---|---|---|
| APEX-Agents | — | 47.5% |
| METR Time Horizons | 49.6% | — |
Reasoning Qwen3.8 27B leads
DeepSeek-V3: 20.5 (#236), Qwen3.8 27B: 41.0 (#54)
| Benchmark | DeepSeek-V3 | Qwen3.8 27B |
|---|---|---|
| CritPt | 0% | 5.4% |
| LMArena Hard Prompts | 1365 | 1460 |
| DTBench | 64.8% | 88% |
| LMCA | 15.5% | 41.4% |
| Epoch Capabilities Index | 135.94 | 149.38 |
| ARC-AGI-2 | — | 42.4% |
| SimpleBench | 27.2% | — |
| Kagi LLM Benchmark | 52.3% | — |
| NYT Connections (extended) | — | 54.5% |
| ARC-AGI-1 | — | 87.5% |
| LiveBench Reasoning | 65.8% | — |
| LiveBench Data Analysis | 60.9% | — |
| Surface Evolver Bench | — | 45% |
| BIG-Bench Hard | 87.5% | — |
| ForecastBench | 59.1 | — |
| HellaSwag | 88.9% | — |
| LiveBench | 66.9% | — |
| PIQA | 84.7% | — |
| WinoGrande | 85.2% | — |
Math Qwen3.8 27B leads
DeepSeek-V3: 32.1 (#219), Qwen3.8 27B: 37.1 (#161)
| Benchmark | DeepSeek-V3 | Qwen3.8 27B |
|---|---|---|
| LMArena Math | 1373 | 1456 |
| OTIS Mock AIME 2024-2025 | 37.8% | — |
| ProofBench | — | 16% |
| Omni-MATH | 40.3% | — |
| LiveBench Math | 73.5% | — |
| MATH Level 5 | 75.5% | — |
| FrontierMath (Feb 2025 set) | 1.7% | — |
Knowledge Qwen3.8 27B leads
DeepSeek-V3: 37.5 (#155), Qwen3.8 27B: 41.6 (#109)
| Benchmark | DeepSeek-V3 | Qwen3.8 27B |
|---|---|---|
| LMArena Expert | 1351 | 1482 |
| GPQA Diamond | 67.6% | — |
| 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% | — |
Multimodal Not comparable
DeepSeek-V3: —, Qwen3.8 27B: 41.3 (#37)
| Benchmark | DeepSeek-V3 | Qwen3.8 27B |
|---|---|---|
| LMArena Vision | — | 1271 |
Multilingual Qwen3.8 27B leads
DeepSeek-V3: 48.5 (#143), Qwen3.8 27B: 53.7 (#60)
| Benchmark | DeepSeek-V3 | Qwen3.8 27B |
|---|---|---|
| LMArena Non-English | 1358 | 1430 |
| LMArena Chinese | 1391 | 1504 |
| LMArena French | 1385 | 1465 |
| LMArena German | 1374 | 1438 |
| LMArena Japanese | 1333 | 1384 |
| LMArena Korean | 1319 | 1393 |
| LMArena Russian | 1373 | 1415 |
| LMArena Spanish | 1358 | 1448 |
Instruction Following Qwen3.8 27B leads
DeepSeek-V3: 72.8 (#130), Qwen3.8 27B: 75.8 (#53)
| Benchmark | DeepSeek-V3 | Qwen3.8 27B |
|---|---|---|
| LMArena Instruction Following | 1345 | 1439 |
| LiveBench Instruction Following | 81.5% | — |
| IFEval | 83.2% | — |
Long Context Qwen3.8 27B leads
DeepSeek-V3: 34.0 (#253), Qwen3.8 27B: 44.3 (#70)
| Benchmark | DeepSeek-V3 | Qwen3.8 27B |
|---|---|---|
| LMArena Longer Query | 1352 | 1450 |
| Fiction.LiveBench | 50% | — |
Writing & Preference Qwen3.8 27B leads
DeepSeek-V3: 57.4 (#130), Qwen3.8 27B: 65.8 (#43)
| Benchmark | DeepSeek-V3 | Qwen3.8 27B |
|---|---|---|
| LMArena Text | 1375 | 1441 |
| LMArena Creative Writing | 1364 | 1384 |
| EQ-Bench Creative Writing | 1472 | 1671 |
| LMArena Multi-Turn | 1389 | 1441 |
| Short-Story Creative Writing | 77% | — |
| WildBench | 83% | — |
| LiveBench Language | 49.1% | — |
Frequently asked questions
Is DeepSeek-V3 better than Qwen3.8 27B?
Qwen3.8 27B is the stronger model overall, scoring 46.0 to 39.5 on the Noometry Index. DeepSeek-V3 costs 2.8× less per token, which makes it the better buy when Qwen3.8 27B's lead doesn't matter for your workload.
Which is cheaper, DeepSeek-V3 or Qwen3.8 27B?
DeepSeek-V3 is cheaper. It lists at $0.24 per million input tokens and $0.90 per million output tokens; Qwen3.8 27B lists at $0.99 and $1.49.
Is DeepSeek-V3 or Qwen3.8 27B better for coding?
Qwen3.8 27B scores higher on coding benchmarks: 50.5 versus 42.3 in the Noometry coding category.
Which has the bigger context window?
Qwen3.8 27B does, with 262K tokens against 164K.
How many benchmarks do DeepSeek-V3 and Qwen3.8 27B share?
23 benchmarks have published results for both models. DeepSeek-V3 has 60 scored results on Noometry and Qwen3.8 27B has 31.