Kimi K2.6

Kimi K2.6 places in the top three on 4 benchmarks.

Moonshot AI Released 20 Apr 2026 Family Kimi K2 The lab's model card

130

Benchmarks with a score

Ranked first, out of five or more models

In the top three

Moonshot AI Apr 2026

Open weights Flagship

151.1 #56 of 271

Epoch Capabilities Index

Where it ranks

Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.

Benchmark	Score	Rank	Source
Phare	76.1%	#7 of 62	Official leaderboard
EQ-Bench 3	1,548	#10 of 78	Official leaderboard
LMArena (Elo)	1,461	#48 of 333	Official leaderboard
Longform Creative Writing (EQ-Bench)	78.5	#18 of 119	Official leaderboard
Humanity's Last Exam	54%	#27 of 147	Model card
BullshitBench V2	65%	#26 of 122	Official leaderboard
Wer wird Millionär? LLM Benchmark	114156.0	#17 of 76	Official leaderboard
WideSearch	80.8%	#4 of 17	Model card
Creative Writing v3	74.7	#33 of 120	Official leaderboard
Extended NYT Connections	87.2%	#29 of 97	Official leaderboard
Judgemark v4	57.3	#22 of 40	Official leaderboard
SimpleQA Verified	34.9%	#55 of 84	Epoch AI
EQ-Bench 4	1,191	#21 of 32	Official leaderboard
Vectara Hallucination Leaderboard (2025 dataset)	10.8%	#69 of 104	Official leaderboard
Document Arena	1,450	#27 of 37	Official leaderboard

Benchmark	Score	Rank	Source
Echo General AI Prediction Leaderboard	1,017	#2 of 17	Official leaderboard
FrontierMath	39%	#10 of 70	Epoch AI
GPQA Diamond	90.8%	#37 of 219	Epoch AI
OTIS Mock AIME 2024-2025	96.1%	#38 of 202	Epoch AI
DTBench	84.9%	#40 of 178	Official leaderboard
FrontierMath Tier 4	14.6%	#15 of 55	Epoch AI
MathArena (Apex, IMO, USAMO)	24%	#13 of 47	Official leaderboard
HMMT 2026	94.7%	#9 of 31	Official leaderboard
IMO-AnswerBench	86%	#11 of 37	Model card
CritPt	8.00%	#65 of 160	Epoch AI
AIME 2026	95.8%	#16 of 31	Official leaderboard
FrontierMath Tiers 1-3 v2	57.2%	#46 of 89	Epoch AI
USAMO 2026	51.2%	#5 of 9	Official leaderboard
ProofBench	16%	#35 of 59	Official leaderboard
ResearchClawBench	18.0	#14 of 23	Official leaderboard
FrontierMath Tier 4 v2	25.6%	#44 of 71	Epoch AI
NatureBench	7.78%	#12 of 18	Official leaderboard
xbench-ScienceQA	65.8%	#25 of 29	Official leaderboard

Benchmark	Score	Rank	Source
LiveCodeBench v6	89.6%	#7 of 76	Model card
SciCode	52.2%	#7 of 47	Model card
OJBench	60.6%	#2 of 12	Model card
LiveSQLBench	29.3%	#10 of 36	Official leaderboard
SWE-bench Verified	76.7%	#10 of 32	Epoch AI
SWE-bench Multilingual	76.7%	#23 of 70	Model card
WeirdML	55.9%	#39 of 112	Official leaderboard
EvoCode-Bench	31.9%	#5 of 13	Official leaderboard
SWE-Bench Pro	58.6%	#30 of 77	Model card
WebDev Arena	1,509	#42 of 105	Epoch AI
ALE-Bench	1,093	#49 of 121	Epoch AI
OpenHands Index	57.1%	#14 of 33	Official leaderboard
FrontierCS	46.9	#6 of 14	Official leaderboard
Code Arena	1,509	#54 of 124	Official leaderboard
EvoCode-Bench v2	13.2%	#6 of 13	Official leaderboard
SlopCodeBench	18.9%	#7 of 14	Official leaderboard
FrontierCode	16%	#6 of 12	Official leaderboard
AndroidBench	67.6%	#18 of 32	Official leaderboard
Code Migration	27.8%	#44 of 78	Official leaderboard
Vibe Code Bench	37.9%	#69 of 115	Official leaderboard
Image-to-WebDev Arena	1,521	#34 of 55	Official leaderboard
GBAEval	0.86%	#17 of 21	Official leaderboard
MLS-Bench	26.7%	#14 of 15	Official leaderboard
SWE-Marathon	0%	#12 of 12	Official leaderboard

Benchmark	Score	Rank	Source
Toolathlon	50%	#7 of 50	Official leaderboard
Terminal-Bench 2.0	66.7%	#12 of 61	Model card
DeepSearchQA	92.5%	#5 of 22	Model card
PACT	1,560	#6 of 26	Official leaderboard
Pencil Puzzle Bench	20%	#13 of 53	Official leaderboard
Claw-Eval	77.9%	#7 of 23	Official leaderboard
Claw-Eval Pass^3	62.3%	#7 of 23	Official leaderboard
BrowseComp	83.2%	#24 of 77	Model card
OSWorld-Verified	73.1%	#11 of 33	Official leaderboard
SkillsBench	54%	#7 of 21	Official leaderboard
DeepTerminalBench	32%	#3 of 9	Official leaderboard
UniClawBench	36.3%	#4 of 10	Official leaderboard
MobileWorld	55.6%	#8 of 18	Official leaderboard
VitaBench 2.0	37.8%	#9 of 20	Official leaderboard
CivBench	1,504	#9 of 18	Official leaderboard
MCPMark	55.9%	#5 of 10	Model card
Toolathlon-Verified	58%	#13 of 25	Official leaderboard
Harbor-Index	8.50%	#5 of 9	Official leaderboard
LiveClawBench	68.6%	#10 of 17	Official leaderboard
CEO-Bench	$43,598	#12 of 19	Official leaderboard
Mystery Game Puzzles	18%	#52 of 80	Epoch AI
OSWorld 2.0	4.60%	#5 of 7	Official leaderboard
Chess Puzzles	20%	#64 of 83	Epoch AI
Long-Horizon-Terminal-Bench 2.0	42%	#13 of 15	Official leaderboard
Long-Horizon-Terminal-Bench (LHTB)	25.5%	#23 of 25	Official leaderboard
EBR-bench	2.38%	#28 of 28	Epoch AI

Benchmark	Score	Rank	Source
CorpFin v2	66.7%	#17 of 119	Official leaderboard
LegalBench	84.7%	#30 of 138	Official leaderboard
Vals Finance Agent	57.1%	#12 of 49	Official leaderboard
TaxEval v2	74.7%	#33 of 129	Official leaderboard
Vending-Bench 2	$6,205	#23 of 66	Official leaderboard
CaseLaw v2	61.2%	#22 of 53	Official leaderboard
MortgageTax	65.8%	#36 of 86	Official leaderboard
Excel Modeling Benchmark	57.9%	#39 of 76	Official leaderboard
EnterpriseClawBench	56.1%	#5 of 9	Official leaderboard
PhysicianBench	17%	#8 of 13	Official leaderboard
Harvey LAB (Legal Agent Benchmark)	1.67%	#50 of 80	Official leaderboard
MedScribe	78.2%	#62 of 98	Official leaderboard
MedCode	40.1%	#63 of 96	Official leaderboard
FORTE	63.9%	#14 of 21	Official leaderboard
APEX-Agents	27.9%	#8 of 12	Model card
Vals Finance Agent v2	44.9%	#56 of 80	Official leaderboard
Tax Agent Bench	12.4%	#60 of 79	Official leaderboard
Legal Research Bench	15.9%	#68 of 88	Official leaderboard
Public Benefits Bench	56.6%	#39 of 50	Official leaderboard
ProfBench	41.4%	#61 of 72	Official leaderboard
E-Commerce Bench	0.70	#17 of 19	Official leaderboard
FrontierFinance	32.3%	#15 of 16	Official leaderboard
PolicyBench	66.9%	#49 of 50	Official leaderboard

Benchmark	Score	Rank	Source
V*	96.9%	#2 of 12	Model card
MMMU-Pro	79.4%	#14 of 72	Model card
Vision Arena	1,265	#34 of 136	Official leaderboard
MATH-Vision (MathVision)	87.4%	#12 of 42	Model card
BabyVision	68.5%	#10 of 27	Official leaderboard
CharXiv	80.4%	#33 of 67	Model card
Claw-Eval-MM	49.6%	#8 of 11	Official leaderboard
Blueprint-Bench 2	3.90%	#30 of 35	Official leaderboard
GDP.pdf	12%	#35 of 39	Epoch AI
Furniture Assembly Benchmark	21.7%	#32 of 35	Epoch AI

Benchmark	Score	Rank	Source
CyberBench (Vals)	74.3%	#9 of 26	Official leaderboard
PCT (Polarized Contrastive Pairs)	43.6%	#21 of 46	Official leaderboard
Human Pathogen Capabilities Test v2 (HPCT v2)	54.5%	#34 of 71	Official leaderboard
Agentic BAIM-LLM Evaluation (ABLE)	42.9%	#12 of 16	Official leaderboard
BiomniBench	59.1	#6 of 8	Official leaderboard
ExploitBench	18%	#7 of 9	Official leaderboard

Benchmark	Score	Rank	Source
SAGE (Vals)	50.2%	#17 of 81	Official leaderboard
ACCoRD	71.4	#42 of 150	Official leaderboard
Conceptual Reasoning Index	53.6	#55 of 149	Official leaderboard
CAIS Vision Capabilities Index	55.3	#22 of 53	Official leaderboard
LMCA	37.3%	#63 of 139	Epoch AI
CAIS Text Capabilities Index	31.4	#33 of 66	Official leaderboard
Vals Multimodal Index	56.4%	#19 of 33	Official leaderboard
CAIS Risk Index	59.5	#49 of 65	Official leaderboard

Moonshot AI's models in color, against every other model on the Epoch Capabilities Index, by release date.

The benchmarks the lab chose to headline, with the scores it gave.