Alex Getmanearly AI signals
Alex Getman @alexgetmancom · · Updated

Tests & comparisons

Kimi K3.1 Pro benchmarks are out!

Kimi K3.1 Pro benchmarks are out!

Of all these benchmarks, I trust Terminal-Bench 4.0 the most.

And the results are impressive:

Kimi K3.1 Pro scores 65.7, just 0.7 points behind the leader, Opus 5.5, while outperforming GPT-6 Astra by 7.5 points.

Screenshot of Kimi K3.1 Pro benchmark results, including Terminal-Bench 4.0 (65.7), where the model trails Opus 5.5 by 0.7 points and outperforms GPT-6 Astra by 7.5 points, plus other tests like Agents' Last Exam and OfficeQA Pro v2.
Kimi K3Moonshot AIKimi
Русская версияMarkdown

Analysis

Related posts