KIMI

MoonshotAI: Kimi K2 Thinking

Kimi / Moonshot AI

54scores
54benchmarks
$0.6 / $2.5 per 1M tokenscost in/out

Metadata

Kimi Closed/API

Aliases: kimi-k2-thinking, kimi-k2-thinking-20251106, moonshotai-kimi-k2-thinking, moonshotai-kimi-k2-thinking-20251106, moonshotai/kimi-k2-thinking, moonshotai/kimi-k2-thinking-20251106

Benchmark Results

Benchmark Category Rank Score Sampled
APEX-Agents Agentic 35 11.50 2026-05-06
Clembench Text v3.0 Agentic 9 77.79 2026-05-06
EnterpriseOps-Gym Agentic 19 19.2% 2026-05-05
Gert Labs Rankings Agentic 49 0.37 2026-05-11
MultiChallenge Agentic 12 55.42 2026-05-06
Poker Agent Agentic 14 1011.634% 2025-12-23
Tau2-Bench Telecom Agentic 42 93% 2026-05-11
Terminal-Bench Hard Agentic 92 31.1% 2026-05-11
VitaBench Agentic 13 12.80 2026-05-06
OpenUGI Alignment 63 52.68 2026-05-06
ALE-Bench Coding 62 597.50 2026-05-06
Arena AI Code Coding 52 1329 2026-05-06
LiveCodeBench Coding 73 63.145% 2026-05-28
Multi-SWE-Bench Coding 4 0.42 2026-05-06
SciCode Coding 66 42.4% 2026-05-11
SWE-bench Verified Coding 43 60.2% 2026-05-28
Terminal-Bench 2.0 Coding 37 37.079% 2026-05-28
CorpFin v2 Finance 46 60.567% 2026-05-28
Finance Agent v1.1 Finance 42 36.647% 2026-05-04
PRBench Finance Finance 12 43.41 2026-05-06
QuantSightBench Finance 8 0.6579 coverage 2026-05-28
TaxEval v2 Finance 50 71.709% 2026-05-28
MMLU-Redux General Knowledge 3 0.94 2026-05-06
WeirdML Generalization 10 42.79 2026-05-06
MedQA Healthcare 29 92.592% 2026-04-16
Omi SOAP Note Safety Benchmark Healthcare 4 4.55 2026-04-21
Artificial Analysis Intelligence Index Intelligence 71 40.89 2026-05-11
GPQA Diamond Intelligence 46 78.536% 2026-05-28
Humanity's Last Exam Intelligence 59 22.3% 2026-05-11
MMLU Pro Intelligence 56 81.068% 2026-05-28
MMLU-Pro Intelligence 36 84.8% 2026-05-11
CaseLaw v2 Legal 11 65.702% 2026-05-04
LegalBench Legal 57 80.201% 2026-05-28
Professional Reasoning Bench - Legal Legal 14 40.90 2026-05-06
AIME Math 36 85.417% 2026-04-16
AIME 2025 Math 11 94.7% 2026-05-11
MGSM Math 42 90.146% 2026-01-09
HMMT 2025 Mathematics 4 0.97 2026-05-06
IMO-AnswerBench Mathematics 12 0.79 2026-05-06
OTIS Mock AIME 2024-2025 Mathematics 10 83.06 2026-05-06
MEDIC Benchmark Medical 19 74.36 average normalized public table score 2026-05-27
Artificial Analysis Openness Index Openness 175 27.78 2026-05-11
CAIS Text Capabilities Index Reasoning 25 18.1 2026-05-27
GPQA Diamond Reasoning 69 83.8% 2026-05-11
OJBench Reasoning 2 0.49 2026-05-06
SimpleBench Reasoning 18 26.30 2026-05-06
CAIS Risk Index Safety 25 57.4 2026-05-27
CritPt Science 55 2.6% 2026-05-11
GSO-Bench Science 5 4.90 2026-05-06
BrowseComp-zh Search 8 0.62 2026-05-06
FRAMES Search 1 0.87 2026-05-06
Seal-0 Search 2 0.56 2026-05-06
Lech Mazur Writing Writing 3 8.69 2026-05-06
WritingBench Writing 15 0.74 2026-05-06