Inference
EN
Moonshot AI

Kimi K2 Instruct

Kimi K2 Instruct is a model from Moonshot AI. 9 benchmarks count toward its index, in 4 categories.

  • Input: text
RankedEnough results for an index.
IndexAll categories, out of 100.43.2±8.9Median 51.0
CoverageIndex weight that has results.65%
SpeedOutput tokens per second.—Median 67/s
First tokenSeconds to the first output token.—Median 1.3 s
Input / 1MUS dollars per 1M input tokens.—Median $0.60
Output / 1MUS dollars per 1M output tokens.—Median $2.55
ContextMaximum tokens in one request.—Median 262K
EloLMArena rating and rank.—Median 1422

Capabilities

Index per category, out of 100.
Out of 100
AgenticMulti-step tasks with tools.2 counted44.6163 / 218
CodingCode writing and repair.3 counted41.3178 / 209
ReasoningLogic problems and puzzles.None counted——
MultimodalTasks with images and text.None counted——
KnowledgeFacts and expert knowledge.2 counted43.6175 / 268
MultilingualTasks in many languages.None counted——
InstructionTasks with strict prompt rules.None counted——
MathMath problems.2 counted43.3117 / 168

Results

9 counted
BenchmarkThe benchmark name.ResultThe score from the source.PlacePlace among results on this benchmark.
MATH 500Math94.2% ±1.010 / 59
Terminal-Bench 1.0Agentic40.0% ±5.522 / 47
SWE-bench Verified · swebench.comCoding43.8%25 / 46
AIMEMath62.7% ±1.256 / 95
LiveCodeBenchCoding70.4% ±1.287 / 142
SWE-bench Verified · SWE-bench/experimentsCoding48.6%41 / 65
GPQA Diamond · Vals AIKnowledge71.5% ±2.391 / 135
MMLU ProKnowledge79.4% ±0.495 / 135
Terminal-Bench 2.0 · Vals AIAgentic25.8% ±4.751 / 66
IOI v1Coding1.3% ±0.658 / 61
MGSMMultilingual90.9% ±1.831 / 74
LegalBenchLegal81.5% ±0.481 / 149
TaxEval v2Finance70.2% ±0.993 / 143
MedQAHealthcare84.0% ±0.362 / 95
CorpFin v2Finance50.4% ±1.0108 / 131

Sources

BenchLMCC BY-NC 4.0Vals AINo licence statedSWE-bench teamNo licence stated

History

5 releases
Index44.2 → 43.2
23 Oct 202612 Nov 2026

Questions

How good is Kimi K2 Instruct?
Its index is 43.2 out of 100. That is place 191 of 283 ranked models.
What is Kimi K2 Instruct best at?
Knowledge: 43.6 out of 100, place 175 of 268.

Badge

Kimi K2 Instruct on Inference360: place 191 of 283, index 43.2
HTML
<a href="https://inference360.ai/models/moonshot-ai-kimi-k2-instruct"><img src="https://inference360.ai/badges/moonshot-ai-kimi-k2-instruct.svg" alt="Kimi K2 Instruct on Inference360: place 191 of 283, index 43.2" height="20"></a>
Markdown
[![Kimi K2 Instruct on Inference360: place 191 of 283, index 43.2](https://inference360.ai/badges/moonshot-ai-kimi-k2-instruct.svg)](https://inference360.ai/models/moonshot-ai-kimi-k2-instruct)

Compare with

GPT-OSS 120B43.4Claude Sonnet 443.0

More from Moonshot AI

All models
Kimi K3.1 Pro75.7Kimi K366.9Kimi K2.658.2Kimi K2.7 Code57.7Kimi K2.5 (Reasoning)53.0