Up to four models
Claude Opus 4.5 vs DeepSeek-V3.2-Speciale
On the index (GPT-4 = 100), Claude Opus 4.5 scores 152 and DeepSeek-V3.2-Speciale 143. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
Claude Opus 4.5
152136–168
WeightsClosed
ReleasedNov 2025
Price in / out$5.0 / $25
Context200K
Core tests taken5 of 9
143125–162
WeightsOpen
ReleasedDec 2025
Price in / out–
Context–
Core tests taken0 of 9
Claude Opus 4.5 and DeepSeek-V3.2-Speciale are too close to call (8 points apart, within the uncertainty).
Test by testthird-party results
Claude Opus 4.5
DeepSeek-V3.2-Speciale
Every result as a table
| Test | Claude Opus 4.5 | DeepSeek-V3.2-Speciale |
|---|---|---|
| Reasoning & knowledge | ||
| SimpleBench | 62.0% | 52.6% |
| Coding | ||
| WeirdML | 63.7% | 46.7% |
Task length · METR45 sec
Tests at least two of these models have taken. Bold rows are the core tests.