Kimi-K3

2 articles tagged with Kimi-K3

October 3, 2026
benchmarkMicrosoft

Microsoft's ThinkingBox: Claude Opus 5.5 passes all 20 runs on just 241 of 507 stateful agent tasks

Microsoft and Hugging Face released ThinkingBox, a benchmark that grades AI agents on the database state they leave behind rather than their responses. Across 507 workflows run 20 times each, Claude Opus 5.5 leads at 67.16% pass@1 but passes all 20 attempts on only 241 tasks.

August 11, 2026
researchOpenAI

Researchers Exploit API Flaw to Read Encrypted Reasoning of OpenAI, Anthropic, Google Models

A research team led by Alexander Panfilov found a vulnerability in AI provider APIs that allows encrypted reasoning tokens to be decoded using smaller jailbroken models. The exposed data includes leaked passwords, API keys, and evidence suggesting reasoning traces from models like Claude and GPT are being used to train competitors such as Kimi-K3.