Kimi K3.1 Pro max delivers stunning Terminal-Bench 4.0 results

Skip to content

Alex Getman @alexgetmancom · 23 Oct 2026, 17:27 UTC · Updated 31 Oct 2026, 20:59 UTC

Tests & comparisons

Kimi's benchmarks are absolutely mind-blowing. Is there a new sheriff in town?

Terminal-Bench 4.0 chart shows Kimi K3.1 Pro max achieving a high TBA score at low cost per task, outperforming GPT-6 Astra max, Claude Opus 5.5, and other models.

Moonshot AI Kimi

Русская версия Markdown

Analysis

AI API pricing: calculate the cost of a finished task