Up to four models
Claude Sonnet 4.5 vs DeepSeek-V3.2-Exp
On the index (GPT-4 = 100), Claude Sonnet 4.5 scores 144 and DeepSeek-V3.2-Exp 140. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
Claude Sonnet 4.5
144129–160
WeightsClosed
ReleasedSep 2025
Price in / out$3.0 / $15
Context1M
Core tests taken6 of 9
140124–157
WeightsOpen
ReleasedSep 2025
Price in / out$0.27 / $0.41
Context164K
Core tests taken0 of 9
Claude Sonnet 4.5 and DeepSeek-V3.2-Exp are too close to call (4 points apart, within the uncertainty), at 20× the price.
Test by testthird-party results
Claude Sonnet 4.5
DeepSeek-V3.2-Exp
Every result as a table
| Test | Claude Sonnet 4.5 | DeepSeek-V3.2-Exp |
|---|---|---|
| Coding | ||
| WeirdML | 47.7% | 39.5% |
| Agents | ||
| DTBench | 83.2% | 87.7% |
| LMCA | 38.8% | 29.1% |
Task length · METR40 sec
Tests at least two of these models have taken. Bold rows are the core tests.