supermarket

Language

Kimi K2

By Moonshot AI, in the Kimi K family.

Released
11 Jul 2025
Status
Legacy
Context
262.1K
Max output
—
Input per 1M tokens
—
Output per 1M tokens
—
Open weights
Yes
License
modified-mit
Parameters
1000B, 32B active
Knowledge cutoff
—
Reasoning
No
Modalities
text → text

Category scores

Out of 100, from independent and third-party results only, by method category-2026-09-29.1.

Category scores
CategoryScoreRankCoverage
Coding & software engineering59.1Not ranked1 of 5
Human preference52.7Not ranked1 of 5

Benchmark results

Every result we hold for this model, with who ran it and where it was published.

Coding & software engineering

Coding & software engineering results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
Aider PolyglotPercent correct59.1%Third party——https://aider.chat/docs/leaderboards/ via Epoch AI
WeirdML (v2)Average accuracy39.4%Third party——WeirdML Leaderboard via Epoch AI
WeirdML (v2)Average accuracy36.7%Third party——https://htihle.github.io/weirdml.html via Epoch AI

Long context

Long context results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
Fiction.LiveBench% correct at 16K tokens (Epoch's column)66.7%Third party——Fiction.live leaderboard via Epoch AI

Human preference

Human preference results
BenchmarkMetricValueProvenanceSettingEvaluatedSource
Text Arena (arena.ai)Arena score (Elo scale)1419Independent—25 Sep 2026Arena
Text Arena (arena.ai)Arena score (Elo scale)1418Independent—25 Sep 2026Arena
Text Arena (arena.ai)Votes26960Independent—25 Sep 2026Arena
Text Arena (arena.ai)Votes11537Independent—25 Sep 2026Arena

Other Kimi K versions

Sources