Up to four models
Qwen3-14B vs DeepSeek-V3.1
On the index (GPT-4 = 100), Qwen3-14B scores 129 and DeepSeek-V3.1 128. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
129113–145
WeightsOpen
ReleasedApr 2025
Price in / out$0.12 / $0.24
Context41K
Core tests taken1 of 9
128111–145
WeightsOpen
ReleasedAug 2025
Price in / out$0.25 / $0.95
Context164K
Core tests taken0 of 9
Qwen3-14B and DeepSeek-V3.1 are too close to call (1 point apart, within the uncertainty), and costs 2.8× less.
Test by testthird-party results
Every result as a table
| Test | Qwen3-14B | DeepSeek-V3.1 |
|---|---|---|
| Reasoning & knowledge | ||
| Fiction.LiveBench | 62.5% | 52.8% |
| Agents | ||
| DTBench | 64.0% | 82.7% |
| LMCA | 18.2% | 24.3% |
Tests at least two of these models have taken. Bold rows are the core tests.