Kimi K3 surpasses Claude Fable 5 in multi-attempt scenarios with better pass@2 and pass@4 performance.
Kimi K3 struggles with reliability in practical tasks despite strong benchmarks, prompting new methods for realistic assessment.
The launch of Kimi K3 sparked a debate regarding its training methods.
Kimi K3 is the largest open-weight model at 2.8 trillion parameters.