RankingEffort benchmarks

Kimi-K2.6 · Reasoning

Compare models

50 measured results · 4 effort settings · 40 benchmark/harness combinations

Model evidence and sources →

Change model

Model

Current configurationSources

Compare with

Choose a second model and its effort to see both profiles and benchmark differences below.

Compare withModel and configuration

Capability profile

One configuration, seven capabilities

Comparison score · 0–100

AKimi-K2.6 · Reasoning5 of 7 capabilities supported

Gaps are unknown, not zero. Hollow points are preliminary.

Agentic
A27.7Supported
Hard reasoning
A37.3Supported
Coding
A30.4Supported
Human pref
Unknown
Knowledge
A28.5Supported
Multimodal
A35.6Supported
Long context
A59.7Preliminary

Each profile belongs to the named configuration. Capability scores use a shared panel for all axes, distinct from the overall ranking panel; they are not accuracy percentages or direct head-to-head wins.

Capability score evidence

Kimi-K2.6 · Reasoning: 23.1 overall comparison score. Meets the overall evidence requirements.

6 areas measured. The available task mix affects this estimate; missing areas remain unknown.

Which sources carry the weight?

Artificial Analysis · 75.0% direct comparison weight · independent of the model provider
Moonshot AI · 25.0% direct comparison weight · provider report

Which benchmark families carry the weight?

Mmmu Pro · 12.1% direct comparison weight
Terminal-Bench · 11.6% direct comparison weight
CharXiv · 6.3% direct comparison weight
SWE-bench Multilingual · 6.3% direct comparison weight
GDPval · 5.4% direct comparison weight
Other families (13) · 58.4% direct comparison weight

These shares describe direct comparison weight, not fractions of the final score or confidence. Source balancing does not give every family equal weight or remove correlations between overlapping sources.

How sensitive is this score?

The audit removes one source at a time and refits against the same overall reference panel. These published results use the matching dataset audited 2026-10-23.

Both ranks use the same surviving configurations for each removal. The cohort starts with 444 configurations supported in the original audit, including separate effort settings. These are diagnostic positions, not the default leaderboard ranks. Eligibility is not rechecked after removal.

What changes when a source is removed?
Removed source	Rank before → after	Rank movement	Cohort remaining / lost support	Score after (change)
Artificial Analysis	Comparison support lost; no rank		203 remaining / 241 lost	Unavailable
ARC Prize	131 → 135	Down 4	444 remaining / 0 lost	26.6 (+3.4 points)
Datacurve	131 → 126	Up 5	444 remaining / 0 lost	21.2 (-1.9 points)
LiveCodeBench	131 → 132	Down 1	444 remaining / 0 lost	23.1 (-0.1 points)
Scale	131 → 135	Down 4	444 remaining / 0 lost	24.2 (+1.0 points)
Terminal-Bench	131 → 129	Up 2	444 remaining / 0 lost	23.6 (+0.4 points)
Cognition	131 → 131	No movement	444 remaining / 0 lost	22.4 (-0.8 points)
LiveBench	130 → 134	Down 4	443 remaining / 1 lost	22.9 (-0.3 points)
SWE-rebench	131 → 131	No movement	444 remaining / 0 lost	23.3 (+0.1 points)
Epoch AI	129 → 135	Down 6	431 remaining / 13 lost	22.9 (-0.2 points)
Vals AI	131 → 129	Up 2	443 remaining / 1 lost	23.0 (-0.1 points)
Provider reports · Anthropic	131 → 131	No movement	444 remaining / 0 lost	23.1 (-0.0 points)
Provider reports · Moonshot AI	131 → 136	Down 5	444 remaining / 0 lost	20.5 (-2.7 points)
Provider reports · Meta	131 → 131	No movement	444 remaining / 0 lost	23.1 (-0.0 points)
Provider reports · Mistral	131 → 131	No movement	444 remaining / 0 lost	23.1 (+0.0 points)
Provider reports · OpenAI	131 → 132	Down 1	444 remaining / 0 lost	23.2 (+0.1 points)
All provider reports	131 → 136	Down 5	444 remaining / 0 lost	20.6 (-2.6 points)

Lost support means a configuration no longer has a comparison path to the complete reference panel. Its rank is unavailable. A surviving path alone does not establish leaderboard eligibility.

Overlapping sources may remain correlated even with source balancing. Leave-one-source-out movement is a sensitivity diagnostic, not a spread of source-specific ranks or a confidence measure. Scoring methodology · Dated configuration audit

Every benchmark family

Removed evidence	Recomputed score	Change
terminal-bench	18.8	-4.4
mmmu-pro	26.8	+3.7
arc-agi	25.8	+2.7
deepswe	21.2	-1.9
gpqa	22.4	-0.8
briefcase	23.9	+0.8
automationbench	23.9	+0.8
frontiercode	22.4	-0.8
aa-lcr	22.4	-0.7
itbench	23.9	+0.7
apex-agents	22.5	-0.7
ifbench	22.5	-0.6
epoch-game-puzzles	22.6	-0.5
tau-bench	22.7	-0.4
simpleqa	23.5	+0.4
gdpval	23.4	+0.3
omniscience	23.4	+0.3
enterprise-ops	23.4	+0.3
mmlu-pro	23.3	+0.2
terminal-bench-science	23.3	+0.2
arc-agi-3	23.0	-0.2
multi-swe-bench	23.0	-0.2
hle	23.3	+0.1
swe-rebench	23.3	+0.1
livebench-instructions	23.3	+0.1
swe-atlas-qna	23.0	-0.1
livebench-language	23.2	+0.1
analyst-agent	23.2	+0.1
livebench-data	23.1	-0.1
swe-atlas-test-writing	23.1	-0.1
aime	23.2	+0.1
frontiermath	23.2	+0.1
critpt	23.1	-0.1
gmmlu	23.2	+0.1
vals-finance-agent	23.1	-0.1
livebench-math	23.2	+0.1
vals-legal-research	23.1	-0.1
livebench-reasoning	23.1	-0.0
vibe-code	23.1	-0.0
vals-tax-agent	23.1	-0.0
enigma-eval	23.1	-0.0
vals-code-migration	23.1	-0.0
math500	23.2	+0.0
gdp-pdf	23.2	+0.0
livecodebench	23.1	-0.0
swe-atlas-refactoring	23.1	-0.0
harvey	23.1	-0.0
vals-excel-modeling	23.1	-0.0
swe-bench-pro	23.1	-0.0
livebench-coding	23.1	+0.0

What evidence is missing from the fit?

Across all collected settings for this model: 139 observations, 32 contributing, 0 matched without graph weight and 107 excluded. Counts do not establish rank eligibility.

2 · Benchmark family or source protocol has not been reviewed
3 · Original SciCode grading defects are under review; retained as supporting evidence, excluded from aggregate and capability scores. Corrected SciCode-Verified requires a separate protocol review. Sources: https://arxiv.org/abs/2608.04975 and https://artificialanalysis.ai/evaluations/scicode
18 · Effort is not identified
1 · Evaluator has not been reviewed for independent admission
10 · No matched opponent in this evaluation unit
1 · Agent swarm execution is not an individual model configuration.
42 · Supporting evidence outside the reviewed capability core
28 · No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately
1 · Microsoft report Table 11 and section 4.1: MAI Terminal-Bench removes timeouts and uses a minimal ReAct harness; comparator values are cited from other model releases. A common evaluation protocol is not established.
1 · Narrow specialist biological, medical or security evaluation; preserved as raw evidence outside general capability scoring.

Inspect every observation and exclusion →

Benchmark results

These are published benchmark scores. Supported effort estimates also appear on the Capability leaderboard. Results from different harnesses occupy different rows. Missing cells stay unknown; no scores are copied between effort levels.

Benchmark / source	High	Reasoning	Non-reasoning	Unspecified
AA-Briefcase EloArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details AA-Briefcase v1.1 is an agentic knowledge work benchmark developed by Artificial Analysis. AA-Briefcase Elo is a combined metric that aggregates rubric pass rate, analytical quality Elo and presentation Elo · Higher is better · Evaluation results measured independently by Artificial Analysis Unit: elo. Source collected 2026-10-18.	Not reported	819.82 Elo Reported settings Kimi K2.6 (Reasoning); Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-6; Mode from evaluator isReasoning metadata; effort budget not specified	Not reported	Not reported
APEX-Agents-AAArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-18.	Not reported	28.47% Reported settings Kimi K2.6 (Reasoning); Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-6; Mode from evaluator isReasoning metadata; effort budget not specified	Not reported	Not reported
AA-LCR v1.1Artificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-18.	Not reported	81% Reported settings Kimi K2.6 (Reasoning); Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-6; Mode from evaluator isReasoning metadata; effort budget not specified	69.67% Reported settings Kimi K2.6 (Non-reasoning); Model source: https://artificialanalysis.ai/models/kimi-k2-6-non-reasoning	Not reported
AutomationBench-AAArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Share of task objectives completed with no guardrail violations · Higher is better · Benchmark developed by Zapier · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-18.	Not reported	13.02% Reported settings Kimi K2.6 (Reasoning); Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-6; Mode from evaluator isReasoning metadata; effort budget not specified	Not reported	Not reported
CritPtArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Benchmark developed by Argonne and UIUC, with contributions from 60+ researchers globally. CritPt is under review by its authors following external feedback · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-18.	Not reported	8% Reported settings Kimi K2.6 (Reasoning); Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-6; Mode from evaluator isReasoning metadata; effort budget not specified	1.43% Reported settings Kimi K2.6 (Non-reasoning); Model source: https://artificialanalysis.ai/models/kimi-k2-6-non-reasoning	Not reported
EnterpriseOps-Gym-AAArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Overall task success rate across all eight enterprise domains (oracle tool mode) · Benchmark developed by ServiceNow Research · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-18.	Not reported	38.53% Reported settings Kimi K2.6 (Reasoning); Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-6; Mode from evaluator isReasoning metadata; effort budget not specified	Not reported	Not reported
GDP.pdf: All-pass RateArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Share of attempts where every atomic criterion passed · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-18.	Not reported	13% Reported settings Kimi K2.6 (Reasoning); Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-6; Mode from evaluator isReasoning metadata; effort budget not specified	Not reported	Not reported
GDPval-AA v2.1 LeaderboardArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Elo rating for performance on real-world work tasks · Anchored to DeepSeek V4.1 Flash (max) at 1600 · Higher is better · Evaluation results measured independently by Artificial Analysis Unit: elo. Source collected 2026-10-18.	Not reported	1,038.29 Elo Reported settings Kimi K2.6 (Reasoning); Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-6; Mode from evaluator isReasoning metadata; effort budget not specified	Not reported	Not reported
GPQA DiamondArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-18.	Not reported	91.11% Reported settings Kimi K2.6 (Reasoning); Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-6; Mode from evaluator isReasoning metadata; effort budget not specified	78.79% Reported settings Kimi K2.6 (Non-reasoning); Model source: https://artificialanalysis.ai/models/kimi-k2-6-non-reasoning	Not reported
Humanity's Last ExamArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-18.	Not reported	37.49% Reported settings Kimi K2.6 (Reasoning); Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-6; Mode from evaluator isReasoning metadata; effort budget not specified	19.56% Reported settings Kimi K2.6 (Non-reasoning); Model source: https://artificialanalysis.ai/models/kimi-k2-6-non-reasoning	Not reported
IFBenchArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-18.	Not reported	75.99% Reported settings Kimi K2.6 (Reasoning); Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-6; Mode from evaluator isReasoning metadata; effort budget not specified	44.29% Reported settings Kimi K2.6 (Non-reasoning); Model source: https://artificialanalysis.ai/models/kimi-k2-6-non-reasoning	Not reported
ITBench-AAArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Combined public and private Site Reliability Engineering (SRE) tasks · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-18.	Not reported	31.19% Reported settings Kimi K2.6 (Reasoning); Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-6; Mode from evaluator isReasoning metadata; effort budget not specified	Not reported	Not reported
MMMU-ProArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-18.	Not reported	79.36% Reported settings Kimi K2.6 (Reasoning); Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-6; Mode from evaluator isReasoning metadata; effort budget not specified	Not reported	Not reported
AA-Omniscience IndexArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details AA-Omniscience Index (higher is better) measures knowledge reliability and hallucination. It rewards correct answers, penalizes hallucinations, and has no penalty for refusing to answer. Scores range from -100 to 100, where 0 means as many correct as incorrect answers, and negative scores mean more incorrect than correct. · Evaluation results measured independently by Artificial Analysis Unit: index. Source collected 2026-10-18.	Not reported	5.3 Reported settings Kimi K2.6 (Reasoning); Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-6; Mode from evaluator isReasoning metadata; effort budget not specified	-9.18 Reported settings Kimi K2.6 (Non-reasoning); Model source: https://artificialanalysis.ai/models/kimi-k2-6-non-reasoning	Not reported
AA-Omniscience AccuracyArtificial Analysis · 6000 questions; 1 attempt; correct-answer share; GPT-5.6 Luna medium grader Benchmark details AA-Omniscience Accuracy (higher is better) measures the proportion of correctly answered questions out of all questions, regardless of whether the model chooses to answer · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-18.	Not reported	32.6% Reported settings Kimi K2.6 (Reasoning); Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-6; Mode from evaluator isReasoning metadata; effort budget not specified	24.3% Reported settings Kimi K2.6 (Non-reasoning); Model source: https://artificialanalysis.ai/models/kimi-k2-6-non-reasoning	Not reported
SciCodeArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Benchmark curated by scientists across 16 disciplines. SciCode is under review following an independent audit of the dataset · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-18.	Not reported	51.5% Reported settings Kimi K2.6 (Reasoning); Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-6; Mode from evaluator isReasoning metadata; effort budget not specified	Not reported	Not reported
𝜏²-Bench TelecomArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-18.	Not reported	95.91% Reported settings Kimi K2.6 (Reasoning); Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-6; Mode from evaluator isReasoning metadata; effort budget not specified	93.86% Reported settings Kimi K2.6 (Non-reasoning); Model source: https://artificialanalysis.ai/models/kimi-k2-6-non-reasoning	Not reported
𝜏³-BankingArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Benchmark developed by Sierra Research · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-18.	Not reported	23.3% Reported settings Kimi K2.6 (Reasoning); Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-6; Mode from evaluator isReasoning metadata; effort budget not specified	Not reported	Not reported
Terminal-Bench HardArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-18.	Not reported	43.94% Reported settings Kimi K2.6 (Reasoning); Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-6; Mode from evaluator isReasoning metadata; effort budget not specified	37.88% Reported settings Kimi K2.6 (Non-reasoning); Model source: https://artificialanalysis.ai/models/kimi-k2-6-non-reasoning	Not reported
Terminal-Bench v2.1Artificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Benchmark developed by the Laude Institute and open-source contributors · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-18.	Not reported	65.92% Reported settings Kimi K2.6 (Reasoning); Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-6; Mode from evaluator isReasoning metadata; effort budget not specified	Not reported	Not reported
Terminal-Bench v4.0Artificial Analysis · mini-SWE-agent v2.4.6; 66 tasks; pass@1 averaged over 3 repeats; 500 steps; task timeout up to 8 hours Benchmark details Benchmark developed by the Laude Institute, Stanford, and open-source contributors · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-18.	Not reported	0.51% Reported settings Kimi K2.6 (Reasoning); Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-6; Mode from evaluator isReasoning metadata; effort budget not specified	Not reported	Not reported
Epoch · Chess Puzzles · v2.0.0Epoch AI · Epoch AI Inspect; task 2.0.0; scorer exact Benchmark details Epoch AI internal evaluation. Mean accuracy under the published setting; exact task version and scorer stay separate. Related tasks share a family budget. Data by Epoch AI, CC BY. Unit: percent. Source collected 2026-10-18.	Not reported	Not reported	Not reported	20% Reported settings Epoch AI Inspect; task 2.0.0; scorer exact; model=kimi-k2.6; run=ehqiuEDETZTqJ8zt6Mc7Ja; mean accuracy; https://epoch.ai/data/benchmarks.csv
Epoch · FrontierMath Tier 4 · v2.0.0Epoch AI · Epoch AI Inspect; task 2.0.0; scorer verification_code Benchmark details Epoch AI internal evaluation. Mean accuracy under the published setting; exact task version and scorer stay separate. Related tasks share a family budget. Data by Epoch AI, CC BY. FrontierMath was developed with OpenAI funding and unequal access to part of the question set; this result is from Epoch's evaluation. Unit: percent. Source collected 2026-10-18.	Not reported	Not reported	Not reported	25.64% Reported settings Epoch AI Inspect; task 2.0.0; scorer verification_code; model=kimi-k2.6; run=eVKA2eavdRAbSN6AnzyBxA; mean accuracy; https://epoch.ai/data/benchmarks.csv
Epoch · FrontierMath Tiers 1–3 · v2.0.0Epoch AI · Epoch AI Inspect; task 2.0.0; scorer verification_code Benchmark details Epoch AI internal evaluation. Mean accuracy under the published setting; exact task version and scorer stay separate. Related tasks share a family budget. Data by Epoch AI, CC BY. FrontierMath was developed with OpenAI funding and unequal access to part of the question set; this result is from Epoch's evaluation. Unit: percent. Source collected 2026-10-18.	Not reported	Not reported	Not reported	57.19% Reported settings Epoch AI Inspect; task 2.0.0; scorer verification_code; model=kimi-k2.6; run=BxrNfyMffkVUq4n7U5eK3Q; mean accuracy; https://epoch.ai/data/benchmarks.csv
Epoch · GPQA diamond · v1.0.8Epoch AI · Epoch AI Inspect; task 1.0.8; scorer choice Benchmark details Epoch AI internal evaluation. Mean accuracy under the published setting; exact task version and scorer stay separate. Related tasks share a family budget. Data by Epoch AI, CC BY. Unit: percent. Source collected 2026-10-18.	Not reported	Not reported	Not reported	90.78% Reported settings Epoch AI Inspect; task 1.0.8; scorer choice; model=kimi-k2.6; run=LjgJoDosTLkiGVT59smA7q; mean accuracy; https://epoch.ai/data/benchmarks.csv

What these comparisons mean

Each source reports its own effort labels. Matching labels do not establish equal compute budgets or identical fallback behavior. Open Reported settings to inspect the exact model name, agent and task coverage. Multiple results at one level remain visible rather than selecting the best. Source-reported None or Non-reasoning labels are not treated as evidence that an API supports those settings.

These measurements use their own dated source collection. The leaderboard fits identified configurations jointly; it contains no pooled model ratings. Explicit thinking budgets are separate configurations. Read the methodology.

Download all effort benchmark results · 8,916 results across 259 models · Collected 2026-10-18

Kimi-K2.6 · Reasoning

Compare with

One configuration, seven capabilities

Agentic

Hard reasoning

Coding

Human pref

Knowledge

Multimodal

Long context

Capability score evidence

Benchmark results