The Model Index
Up to four models

GPT-5.1 vs DeepSeek-V3.2-Speciale

On the index (GPT-4 = 100), GPT-5.1 scores 150 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 GPT-5.1
Presets
GPT-5.1
150134–166
WeightsClosed
ReleasedNov 2025
Price in / out$1.25 / $10
Context400K
Core tests taken4 of 9
DeepSeek-V3.2-Speciale
143125–162
WeightsOpen
ReleasedDec 2025
Price in / out–
Context–
Core tests taken0 of 9

GPT-5.1 and DeepSeek-V3.2-Speciale are too close to call (7 points apart, within the uncertainty).

Test by testthird-party results

GPT-5.1DeepSeek-V3.2-Speciale
0%25%50%75%100%REASONING & KNOWLEDGESimpleBenchSimpleBenchCODINGWeirdMLWeirdML
Every result as a table
TestGPT-5.1DeepSeek-V3.2-Speciale
Reasoning & knowledge
SimpleBench53.2%52.6%
Coding
WeirdML60.8%46.7%

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

This page as a chartDownload PNG