AI Rankings

Moonshot AI

Kimi K3

Moonshot AI's 2.8T-parameter mixture-of-experts model and the highest-scoring open-weight entry on the Artificial Analysis Intelligence Index.

Visit official site (opens in a new tab)Compare with another model

Our editorial assessment, based on the public sources listed below. Last reviewed .

Overall rank
#18
Tier
A
Score
85.0
Main category
Overall

Strengths

  • Highest-ranked open-weights model on the Artificial Analysis Intelligence Index v4.1
  • 2.8T total parameters with 104B active at inference and a 1M-token context window
  • Fifth overall on the August 2026 BenchAlign leaderboard, ahead of several closed frontier models

Considerations

  • Self-hosting a 2.8T MoE checkpoint requires serious multi-GPU infrastructure
  • Official API price ($3 input / $15 output per 1M tokens) is above many other open-weight options

Price

Open weights on Hugging Face; API $3 input / $15 output per 1M tokens ($0.30 cached input)

Shown for reference — price is not part of the score.

Score breakdown

Performance
87.0
55% of score
Reputation
86.0
35% of score
Recency
70.0
10% of score

The overall score combines these sub-scores using the weights shown. How we score →

Verification status

Each field carries its own re-verification date. Amber means older than 90 days — treat those figures as stale until re-checked.

Pricing
Benchmark
Reputation
Feature list

Checked against the sources listed below.

Sources

Show 9 more sources

Similar models