Skip to content
AIWorkBench.fr

Model

Kimi K3 evaluated on the hub's 2 benchmarks

Released on 16 July 2026, Kimi K3 (Moonshot AI) joins the hub's rankings: its place on the Business Index, its strongest and weakest business functions, its cost and its hallucination rate.

Report written by the hub from the published rankings: every sentence is computed, none is an opinion.

  • 17th of 27 on the Business Index, at 96.8% (95% margin of error: ± 3.0 points).
  • 3.2 index points below Kimi K2.6, its predecessor at Moonshot AI, released on 20 April 2026.
  • Mean cost per test: $0.017, the 23rd cheapest of the 27 models with a known price.
  • Mean hallucination rate: 0.5%, the share of items missing from the source for which it invented a value.
  • It took all 2 of the hub's benchmarks.

Scores by business function

The model's mean accuracy on the benchmarks it took in each business function.

Business functionScore
Finance93.8%
Accounting99.8%
Human resourcesNot tested
LegalNot tested
SalesNot tested
MarketingNot tested
Customer serviceNot tested
Procurement & logisticsNot tested
ITNot tested
ManagementNot tested
Business Index96.8%