LLM comparison · detail

Kimi K3

Provider: Moonshot

Model type: specialist Budget: mid-budget Use it for: coding Use it for: large batches Use it for: company knowledge

coding pick backed by current AA.

Verdict “Kimi K3 has IQ 43.6 and input $3/M in the sources. Consider it for coding, large batches; for enterprise-governance, tool-use, run a second benchmark before rollout.”

Snapshot summary

Moonshot AI is the Chinese company behind Kimi, best known for long context and cheaper models for high-volume text work. Kimi K3 is a Moonshot model that has moved up into the frontier challenger pack. It fits coding and long-context work, but the pricing is now mid-tier, not a cheap-volume coupon.

In this compare snapshot it is tagged mainly for coding, batch, rag, with price tier mid and context window is unavailable in verified data. The negative side matters too: watch enterprise-governance, tool-use. Use the numbers below as the hard boundary, because this profile explains the model, it does not replace benchmark provenance.

Figures below, fetched from source artificial_analysis (fetched 2026-09-24T04:00:35Z).

Snapshot figures

$3/M input artificial_analysis:kimi-k3

$15/M output artificial_analysis:kimi-k3

43.6 intelligence index artificial_analysis:kimi-k3

What this means

✓ Good for: coding · large batches · company knowledge

✗ Not for: company controls and audit · reliable tool use

Source and provenance

Data source: artificial_analysis
Fetched: 2026-09-24T04:00:35Z
Status per metric: price: artificial_analysis:kimi-k3; IQ: artificial_analysis:kimi-k3; Elo: curated_seed; Aider: curated_seed; DeepSWE: curated_seed

This page shows only verified data from the current snapshot.