Skip to content
llmwaves

Kimi K2 0711

Moonshot AI · released Jul 11, 2025

Open weightsTool use

Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for...

Specification

Context window
131K
Max output
100K
Knowledge cutoff
Dec 31, 2024
Parameters
1026.5B
Licence
other
Serving providers
1
Moderated
No
Uptime
99.9%

Intelligence

19.7

59th percentile

Coding

Coding Index

Agentic

Agentic Index

Output speed

21 t/s

Median across providers

Latency

942ms

Time to first token

Cost per task

$0.09

Estimated

Benchmarks

Where the score comes from

The Intelligence Index is a composite. These are the underlying evaluations this model was actually measured on.

Evaluation scores

Percentage correct · higher is better

  • MMLU-Pro
    82.4%
  • GPQA Diamond
    76.6%
  • τ²-bench (Telecom)
    61.1%
  • AIME 2025
    57.0%
  • LiveCodeBench
    55.6%
  • AA-LCR (long context)
    53.0%
  • IFBench
    41.5%
  • SciCode
    34.5%
  • Terminal-Bench Hard
    15.9%
  • Humanity's Last Exam
    7.4%

An evaluation missing from this list was not run for this model — it is not a zero.

View as table
EvaluationScore
MMLU-Pro82.4%
GPQA Diamond76.6%
τ²-bench (Telecom)61.1%
AIME 202557.0%
LiveCodeBench55.6%
AA-LCR (long context)53.0%
IFBench41.5%
SciCode34.5%
Terminal-Bench Hard15.9%
Humanity's Last Exam7.4%

Against its peers

Intelligence Index · this model highlighted, nearest peers in grey

Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.

View as table
ModelIntelligence
R120.4
North Mini Code (free)20.2
GPT-5 Nano20.1
Kimi K2 071119.7
GLM 4.519.7
GPT-4.119.6
o3 Mini19.2
o1-pro19.1

Percentile among all indexed models

Intelligence59th
Mathematics54th
Terminal work53th
Arena Elo34th

Pricing

What it costs to run

List prices per million tokens, plus what one representative task works out to.

List price

Input / 1M tokens
$0.57
Output / 1M tokens
$2.3
Cached input / 1M
Not offered
Blended 3:1
$1

One task, estimated

$0.09

Input tokens
50,000
Output tokens
25,000
Profile
Standard

Estimated from list pricing: 50K input tokens plus 80K output tokens for reasoning models (25K for non-reasoning).

Serving providers

Speed and latency figures are medians across these providers, so a widely-served model reports a blend rather than any single endpoint.

Arena

Head-to-head generation quality

Elo from pairwise judgements, broken out by the kind of thing the model was asked to build.

Overall Elo
1,135
Win rate
48.8%
Strongest at
Websites
Tournaments
713

Elo by category

Dot position on a 1,125–1,150 scale · Elo has no meaningful zero

1,1251,150

Agent categories (full-stack apps, mobile apps) are only scored for models tested in agent harnesses.

View as table
CategoryEloWin rate
Websites113548.8%