RankingIA v0.6.1
EN

Kimi K3open

Moonshot AI

56.4#98 of 427 overall
Input / output
US$ 0,19 / US$ 15,00
US$ per 1M tokens
Context
1.0M
tokens
Release
07/16/2026
release date
Speed
0 tok/s
first token in 0.00 s

Family history

The 4 versions of this family, from first to newest, by release date. Click a point to open that version.

See the data as a table
ModelReleasedScoreRankAA Intel.Elo Arena
Kimi K2 Thinking11/06/202550.2#148—1380
Kimi K2.501/27/202664.7#64—1445
Kimi K2.604/20/202667.7#51—1456
Kimi K307/16/202656.4#9817.41476

Scores by source

Scores by sourcepercentile = % of ranked models it beats
MetricValuePercentileSource
LiveBench weight 3 64.6 45% LiveBench
AA Intelligence Index weight 3 17.4 26% Artificial Analysis
Arena text (Elo) weight 2 1476 90% LMArena
Arena WebDev (Elo) weight 1 1656 88% LMArena
Humanity's Last Exam weight 1 25.0 74% Artificial Analysis
Terminal-Bench weight 1 12.6 74% Artificial Analysis
GPQA Diamond 84.2 75% Artificial Analysis
Long-context reasoning 79.3 84% Artificial Analysis
LiveBench long agentic 26.4 39% LiveBench
LiveBench reasoning 90.7 74% LiveBench
LiveBench coding 59.3 3% LiveBench
LiveBench browser 75.2 68% LiveBench
LiveBench data analysis 78.7 65% LiveBench
LiveBench research 79.0 55% LiveBench
LiveBench design 77.2 53% LiveBench

By category

CategoryScoreRankMetrics
Agentic54.2#54LiveBench long agentic, Terminal-Bench
Coding46.9#65LiveBench coding, Arena WebDev (Elo)
Reasoning68.4#86LiveBench reasoning, Humanity's Last Exam, GPQA Diamond
Data analysis57.3#12LiveBench data analysis
Research62.9#78LiveBench research, Long-context reasoning
Design63.6#25LiveBench design, Arena WebDev (Elo)
Browser use58.9#11LiveBench browser
Chat69.8#21Arena text (Elo)

History

RankingIA score on each collection day (hover to see the rank).

Daily collection started on 10/30/2026. The chart appears from the second day the model is ranked.

Compare with other models

At the sources