Skip to content
ENTITY PROFILE / KNOWLEDGE GRAPH

Kimi K3

RSS

Mistral Large 4 was ahead of Kimi K3 in the blind human evaluation Kimi-K3 outperforms Claude Opus 5.5 on the ThinkingBox benchmark Hebbia uses Nemotron 3.5 Super VL to analyze credit agreements Deepseek V4.1-Flash-1017 outperforms Kimi K3 Moonshot AI released the Chinese model Kimi K3 Kimi K3.1 Pro outperforms Kimi K3 by 11 points on the Artificial Analysis Intelligence Index Kimi K3.1 Pro is a post‑trained version of Kimi K3· Entity summary generated by Graphiti

RELATIONS
10Relations
CURRENT
8Current
EVENTS
4Events
REPORTS
8Source reports
KNOWLEDGE ATLAS0 entities · 0 relations
No public neighbors yet
Explore all published links of a node; previously discovered relations remain visible.

Relation timeline

BY VALID-FROM DATE
  1. Kimi K3.1 ProIS POST TRAINED VERSION OFKimi K3

    Kimi K3.1 Pro is a post‑trained version of Kimi K3

    Current1 sourceKimi K3.1 Pro
  2. Kimi K3.1 ProOUTPERFORMS BY POINTSKimi K3

    Kimi K3.1 Pro outperforms Kimi K3 by 11 points on the Artificial Analysis Intelligence Index

    Current1 sourceKimi K3.1 Pro
  3. MOONSHOTRELEASEDKimi K3

    Moonshot AI released the Chinese model Kimi K3

    Current1 sourceMOONSHOT
  4. Deepseek V4.1-Flash-1017OUTPERFORMSKimi K3

    Deepseek V4.1-Flash-1017 outperforms Kimi K3

    Ended 2026-10-201 sourceDeepseek V4.1-Flash-1017
  5. Muse Spark OpenBENCHMARKED WITHKimi K3

    Muse Spark Open was benchmarked against Kimi K3

    Current1 sourceMuse Spark Open
  6. Muse Spark OpenOUTPERFORMSKimi K3

    Muse Spark Open scores well ahead of Kimi K3 on several categories

    Current2 sourcesMuse Spark Open
  7. Muse Spark OpenANSWERSKimi K3

    Muse Spark Open is Meta's answer to Kimi

    Current1 sourceMuse Spark Open
  8. Kimi K3USINGNemotron 3.5 Bolt 74B-A9B 24GB

    Hebbia uses Nemotron 3.5 Super VL to analyze credit agreements

    Current1 sourceNemotron 3.5 Bolt 74B-A9B 24GB
  9. Mistral Large 4SURPASSEDKimi K3

    Mistral Large 4 was ahead of Kimi K3 in the blind human evaluation

    Current1 sourceMistral Large 4
  10. Kimi K3OUTPERFORMSClaude Opus 5

    Kimi-K3 outperforms Claude Opus 5.5 on the ThinkingBox benchmark

    Ended 2026-10-131 sourceClaude Opus 5

Relations are facts Graphiti extracted from reports, not verbatim quotes. An end date means later reporting showed the relation no longer holds.

Events 4

Source reports 8