Kimi K2.6

Across the task benchmarks we track, Kimi K2.6’s strongest relative results are in coding, terminal use, and reasoning. On SWE-bench Verified, it scores 80.2%, ranking #3 among 7 models with reported results in our dataset.

Updated: Nov 5, 2026Data as of: Nov 2, 2026

Compare this model

Strongest results

Strongest results for Kimi K2.6 in tracked evaluation cohorts
Benchmark	Measures	Score
SWE-bench ↗Verified / published open-model reports	Coding	80.2%#3 of 7
IFBench ↗58 constraint types	Precise instruction following	75.99%#8 of 17
GPQA ↗Diamond / Artificial Analysis	Reasoning	91.11%Joint #17 of 30
BrowseComp ↗Published open-model reports	Web research	83.2%#5 of 8

Model details

Open source / open weights14 benchmarks

Specifications for Kimi K2.6
Model	Kimi K2.6
Agent Index v1.2	Insufficient coverage (3/7) · Preview
Creator	Moonshot AI (opens in a new tab)
Availability	Open source / open weights
Context size	256,000 tokens (opens in a new tab)
Max output	Not reported
Knowledge cutoff	Not reported
License	Modified MIT · Model weights ↗ (opens in a new tab)

Pricing and performance

Per provider and reported configuration. Prices are USD per 1M tokens.

Provider offerings for Kimi K2.6
Provider / configuration	Contexttokens	InputUSD / 1M tokens	OutputUSD / 1M tokens	LatencyTTFT · seconds	Speedtokens / sec
Moonshot AI (opens in a new tab) Kimi K2.6 (Reasoning)	256,000	$0.95 (opens in a new tab)	$4.00 (opens in a new tab)	2.834 (opens in a new tab)	40.714 (opens in a new tab)

Benchmark performance

Kimi K2.6 in color, alongside leading models. Latest stored reports, best effort per report date.

Reasoning

198-question Diamond subset; independent AA evaluation

GPQA Diamond ↗

01
GPT-6 Astra96.3%
02
Gemini 3.8 Flash95.3%
03
Gemini 3.1 Pro94.1%
03
GPT-5.6 Sol94.1%
03
Muse Spark 1.394.1%
17
Kimi K2.6This model91.1%

Coding

Verified split; published reports

SWE-bench Verified ↗

Terminal Use

89 tasks; Terminus 2; e2b; three repeats

Terminal-Bench 2.1 ↗

01
Kimi K385%
02
GLM-5.3-Flash84.3%
03
GLM-5.383.9%
04
DeepSeek V4 Pro 081378.7%
05
GLM-5.277.9%
06
Kimi K2.6This model65.9%

Web Research

Published reports; source settings retained

BrowseComp ↗

Work Automations

Private 657 tasks; 50 turns; objective completion

AutomationBench-AA ↗

01
Gemini 4 Carbon77.8%
02
Gemini 4 Argon77.5%
03
Kimi K3.1 Pro73.3%
04
MiniMax M3.1 Flash72.52%
05
Claude Sonnet 5.571.8%
47
Kimi K2.6This model13.02%

Knowledge Work

220 tasks; Stirrup agent; pairwise Elo

GDPval-AA v2.1 ↗

01
Claude Opus 5.51,866 Elo
02
Kimi K3.1 Pro1,858 Elo
03
Claude Sonnet 5.51,838 Elo
04
Claude Fable 5.11,763 Elo
05
DeepSeek V4.1 Flash 10171,746 Elo
31
Kimi K2.6This model1,047 Elo

Reported benchmarks

All published results in our dataset, with versions, evaluation settings, and sources.

All published benchmark reports for Kimi K2.6
Benchmark	Score	Evaluation setup	Source
AA-Briefcase1.1 / combined EloCombined Elo · Higher is better	820.03 Elo	selection: best reported configuration per release · Kimi K2.6 (Reasoning) · tools: benchmark-defined	Artificial Analysis (opens in a new tab)independent
AutomationBench-AA1.0.6 / AA private 657Objectives completed without guardrail violations · Higher is better	13.021%	Kimi K2.6 (Reasoning); Private 657 tasks; 50 turns; objective completion	Artificial Analysis (opens in a new tab)independent
BrowseCompPublished open-model reportsAccuracy · Higher is better	83.2%	harness comparison: provider-reported; settings differ across models · Moonshot provider-reported tool-augmented BrowseComp	Moonshot AI ↗ (opens in a new tab)provider reported
GDP.pdf100 tasks / All-pass / five attemptsAccuracy · Higher is better	13%	selection: best reported configuration per release · Kimi K2.6 (Reasoning) · tools: benchmark-defined	Artificial Analysis (opens in a new tab)independent
GDPval-AA2.1Elo · Higher is better	1,046.53 Elo	Kimi K2.6 (Reasoning); 220 tasks; Stirrup agent; pairwise Elo	Artificial Analysis (opens in a new tab)independent
GPQADiamond / Artificial AnalysisAccuracy · Higher is better	78.788%	Kimi K2.6 (Non-reasoning); 198-question Diamond subset; independent AA evaluation	Artificial Analysis (opens in a new tab)independent
GPQADiamond / Artificial AnalysisAccuracy · Higher is better	91.111%	Kimi K2.6 (Reasoning); 198-question Diamond subset; independent AA evaluation	Artificial Analysis (opens in a new tab)independent
Humanity's Last ExamHLE — source does not specify subsetAccuracy · Higher is better	54%	Provider announcement; tools enabled; subset not explicitly named in announcement · Tools enabled	Moonshot AI ↗ (opens in a new tab)provider reported
Humanity's Last ExamStable HLE — text-only subsetAccuracy · Higher is better	19.555%	Kimi K2.6 (Non-reasoning); original HLE text-only 2,158 questions; no tools; not HLE Diamond · No tools	Artificial Analysis (opens in a new tab)independent
Humanity's Last ExamStable HLE — text-only subsetAccuracy · Higher is better	37.488%	Kimi K2.6 (Reasoning); original HLE text-only 2,158 questions; no tools; not HLE Diamond · No tools	Artificial Analysis (opens in a new tab)independent
IFBench58 constraint typesAccuracy · Higher is better	75.986%	selection: best reported configuration per release · Kimi K2.6 (Reasoning) · tools: benchmark-defined	Artificial Analysis (opens in a new tab)independent
SWE-benchVerified / published open-model reportsResolved · Higher is better	80.2%	harness comparison: provider-reported; settings differ across models · Kimi K2.6 Thinking; quoted comparison table; follow original Kimi SWE harness	MiniMax ↗ (opens in a new tab)provider reported
Terminal-Bench2.0 / published open-model reportsTask success · Higher is better	66.7%	harness comparison: provider-reported; settings differ across models · Published Terminal-Bench 2.0 score; not 2.1	Moonshot AI ↗ (opens in a new tab)provider reported
Terminal-Bench2.1 / Artificial AnalysisPass@1 · Higher is better	65.918%	Kimi K2.6 (Reasoning); 89 tasks; Terminus 2; e2b; three repeats	Artificial Analysis (opens in a new tab)independent
Terminal-Bench4.0 / mini-swe-agentTask success · Higher is better	0.505%	harness: mini-swe-agent · repeats: 3 · selection: best reported configuration per release · Kimi K2.6 (Reasoning)	Artificial Analysis (opens in a new tab)independent
π-BenchOverall · PROCProactivity (PROC) · Higher is better	63.8%	completeness score: 62 · completeness uncertainty: 1.2 · metric: Avg PROC · personas: 5 · proc uncertainty: 1.3 · selection: Overall rows; not per-persona averages. COMP is a separate metric and does not determine this ranking. · tasks: 100	π-Bench research team ↗ (opens in a new tab)benchmark publisher