GeekRadar / The comparison desk

COMPARE.

AI

Filters

Filter AI models

Rank by benchmark Clear all filters

Best result per entry; configurations may differ.

anthropic

Claude Opus 4.6

Models

Context window: 1,000,000 tokens
Maximum output: 128,000 tokens
Open weights: No
Maximum input: 1,000,000 tokens^*

2026-02-05

Software engineering QwenSWEBench · version unreported · reported score · Claude Code · Internal · max · avg@3#1^* · 63.80^*Platform unreported

ECI 156.3^*General capability index

* Provisional data