EBEasy BenchmarksLLM model index
Workspace
Overview
Benchmarks
Benchmarks list
Overall Index
Coding
Math
MMLU-Pro
Speed
Value
Models
All models
GPT-5.5 (xhigh)
GPT-5.5 (high)
Claude Opus 4.7 (Adaptive Reasoning, Max Effort)
Gemini 3.1 Pro Preview
GPT-5.4 (xhigh)
Artificial Analysis data
Back

Kimi

Kimi K2

Kimi K2 is a Kimi language-model profile in the Easy Benchmarks snapshot. Use this page to compare its measured Artificial Analysis scores, output speed, time to first token, pricing, and relative ranking against other models in the local catalog.

Kimi model releases

Operational Metrics

Output Speed33 tok/s
First Token1.23s
Blended Price$1.04/M

Model Metadata

Queryable facts extracted from the upstream model payload.

ReleaseJul 11, 2025
Context Windown/a
Modalitiesn/a
API fields: release_date

Strength: MATH-500

Rank #26 across 201 models.

97.1%

Strength: MMLU-Pro

Rank #68 across 345 models.

82.4%

Strength: AIME

Rank #41 across 194 models.

69.3%

Watch Area: Speed

Rank #273 across 293 models.

33 tok/s

Strength Profile

Percentile score by analysis domain.

* Cost is inverted: lower input, output, and blended prices rank higher.

Benchmark Percentiles

Higher bars mean stronger relative placement.

All Benchmarks

MetricDomainValueRank
Artificial Analysis Intelligence Indexoverall26.3#176
Artificial Analysis Coding Indexcoding22.1#176
Artificial Analysis Math Indexmath57.0#124
MMLU-Proreasoning82.4%#68
GPQA
reasoning
76.6%
#140
Humanity's Last Examreasoning7.0%#211
LiveCodeBenchcoding55.6%#130
SciCodecoding, reasoning34.5%#196
MATH-500math97.1%#26
AIMEmath69.3%#41
Output Speedspeed33 tok/s#273
Time to First Tokenspeed1.23s#175
Blended Pricecost$1.04/M#178
Input Pricecost$0.585/M#176
Output Pricecost$2.40/M#167
Value Indexcost, overall25.3#172