The Model Index
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.

Next to Claude Opus 4.5
Presets
Claude Opus 4.5
152136–168
WeightsClosed
ReleasedNov 2025
Price in / out$5.0 / $25
Context200K
Core tests taken5 of 9
DeepSeek-V3.2-Speciale
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 4.5DeepSeek-V3.2-Speciale
0%25%50%75%100%REASONING & KNOWLEDGESimpleBenchSimpleBenchCODINGWeirdMLWeirdML
Every result as a table
TestClaude Opus 4.5DeepSeek-V3.2-Speciale
Reasoning & knowledge
SimpleBench62.0%52.6%
Coding
WeirdML63.7%46.7%
Task length · METR45 sec

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

This page as a chartDownload PNG