The Model Index
Up to four models

Compare

Side by side on the same independent tests, with price and context. The link in your address bar shares this exact comparison.

Next to DeepSeek-V3.2-Speciale
Presets
DeepSeek-V3.2-Speciale
147128–165
WeightsOpen
ReleasedDec 2025
Price in / out–
Context–
Core tests taken0 of 9
GPT-5.2
166150–183
WeightsClosed
ReleasedDec 2025
Price in / out$1.75 / $14
Context400K
Core tests taken6 of 9

GPT-5.2 leads DeepSeek-V3.2-Speciale by 20 points.

Test by testindependent results

DeepSeek-V3.2-SpecialeGPT-5.2
0%25%50%75%100%REASONING & KNOWLEDGESimpleBenchSimpleBenchCODINGWeirdMLWeirdML
Task length · METR45 sec

Tests at least two of these models have taken. Bold rows are the core tests.