RankingEffort benchmarks

Kimi-K2.7-Code · Reasoning

Compare models

31 measured results · 3 effort settings · 31 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-K2.7-Code · Reasoning3 of 7 capabilities supported

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

Agentic
A27.8Supported
Hard reasoning
A34.3Supported
Coding
A32.8Preliminary
Human pref
Unknown
Knowledge
A20.9Supported
Multimodal
Unknown
Long context
A47.2Preliminary

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-K2.7-Code · Reasoning: 19.0 overall comparison score. Meets the overall evidence requirements.

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

Which sources carry the weight?

Artificial Analysis · 100.0% direct comparison weight · independent of the model provider

Which benchmark families carry the weight?

IFBench · 8.8% direct comparison weight
Humanity’s Last Exam · 8.6% direct comparison weight
GPQA · 8.6% direct comparison weight
Critpt · 8.5% direct comparison weight
omniscience · 8.5% direct comparison weight
Other families (8) · 57.0% 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 2026-10-20.

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	142 → 143	Down 1	444 remaining / 0 lost	23.2 (+4.1 points)
Datacurve	142 → 141	Up 1	444 remaining / 0 lost	15.7 (-3.3 points)
LiveCodeBench	142 → 143	Down 1	444 remaining / 0 lost	18.9 (-0.1 points)
Scale	142 → 141	Up 1	444 remaining / 0 lost	21.1 (+2.1 points)
Terminal-Bench	142 → 141	Up 1	444 remaining / 0 lost	18.9 (-0.1 points)
Cognition	142 → 142	No movement	444 remaining / 0 lost	18.2 (-0.8 points)
LiveBench	141 → 142	Down 1	443 remaining / 1 lost	19.6 (+0.5 points)
SWE-rebench	142 → 141	Up 1	444 remaining / 0 lost	19.4 (+0.3 points)
Epoch AI	140 → 140	No movement	431 remaining / 13 lost	19.4 (+0.3 points)
Vals AI	142 → 141	Up 1	443 remaining / 1 lost	18.4 (-0.7 points)
Provider reports · Anthropic	142 → 142	No movement	444 remaining / 0 lost	19.0 (-0.0 points)
Provider reports · Moonshot AI	142 → 143	Down 1	444 remaining / 0 lost	18.6 (-0.5 points)
Provider reports · Meta	142 → 142	No movement	444 remaining / 0 lost	19.0 (-0.0 points)
Provider reports · Mistral	142 → 142	No movement	444 remaining / 0 lost	19.0 (+0.0 points)
Provider reports · OpenAI	142 → 142	No movement	444 remaining / 0 lost	19.2 (+0.1 points)
All provider reports	142 → 143	Down 1	444 remaining / 0 lost	18.7 (-0.4 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
arc-agi	22.5	+3.5
deepswe	15.7	-3.3
ifbench	20.2	+1.2
mmmu-pro	20.1	+1.1
aa-lcr	18.0	-1.0
gpqa	18.1	-0.9
frontiercode	18.2	-0.8
briefcase	19.8	+0.8
epoch-game-puzzles	18.3	-0.7
simpleqa	19.7	+0.7
hle	19.7	+0.7
omniscience	18.5	-0.6
critpt	18.6	-0.4
mmlu-pro	19.5	+0.4
swe-rebench	19.4	+0.3
gdpval	19.4	+0.3
livebench-instructions	19.3	+0.3
enterprise-ops	18.7	-0.3
multi-swe-bench	18.7	-0.3
gdp-pdf	19.3	+0.3
terminal-bench	18.8	-0.3
livebench-language	19.3	+0.2
apex-agents	19.3	+0.2
terminal-bench-science	19.2	+0.2
arc-agi-3	18.8	-0.2
harvey	18.8	-0.2
swe-atlas-qna	18.8	-0.2
enigma-eval	18.9	-0.2
analyst-agent	19.2	+0.2
automationbench	18.9	-0.2
livebench-coding	18.9	-0.2
tau-bench	19.2	+0.1
itbench	18.9	-0.1
vibe-code	18.9	-0.1
livebench-reasoning	18.9	-0.1
swe-atlas-test-writing	19.0	-0.1
gmmlu	19.1	+0.1
vals-legal-research	19.0	-0.1
livecodebench	19.0	-0.1
vals-finance-agent	19.0	-0.1
aime	19.0	-0.1
vals-code-migration	19.0	-0.1
vals-tax-agent	19.0	-0.0
math500	19.1	+0.0
vals-excel-modeling	19.0	-0.0
frontiermath	19.1	+0.0
livebench-math	19.0	+0.0
swe-atlas-refactoring	19.0	-0.0
swe-bench-pro	19.0	+0.0
livebench-data	19.0	-0.0

What evidence is missing from the fit?

Across all collected settings for this model: 35 observations, 17 contributing, 0 matched without graph weight and 18 excluded. Counts do not establish rank eligibility.

1 · Benchmark family or source protocol has not been reviewed
1 · 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
10 · Effort is not identified
2 · Evaluator has not been reviewed for independent admission
3 · Supporting evidence outside the reviewed capability core
1 · No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately

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	Max	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	858.75 Elo Reported settings Kimi K2.7 Code; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-7-code; Mode from evaluator isReasoning metadata; effort budget not specified	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	79.33% Reported settings Kimi K2.7 Code; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-7-code; Mode from evaluator isReasoning metadata; effort budget not specified	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	24.45% Reported settings Kimi K2.7 Code; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-7-code; Mode from evaluator isReasoning metadata; effort budget not specified	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	10% Reported settings Kimi K2.7 Code; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-7-code; Mode from evaluator isReasoning metadata; effort budget not specified	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	40.23% Reported settings Kimi K2.7 Code; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-7-code; Mode from evaluator isReasoning metadata; effort budget not specified	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	11.2% Reported settings Kimi K2.7 Code; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-7-code; Mode from evaluator isReasoning metadata; effort budget not specified	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	1,037.51 Elo Reported settings Kimi K2.7 Code; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-7-code; Mode from evaluator isReasoning metadata; effort budget not specified	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	89.6% Reported settings Kimi K2.7 Code; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-7-code; Mode from evaluator isReasoning metadata; effort budget not specified	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	35.03% Reported settings Kimi K2.7 Code; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-7-code; Mode from evaluator isReasoning metadata; effort budget not specified	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	63.13% Reported settings Kimi K2.7 Code; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-7-code; Mode from evaluator isReasoning metadata; effort budget not specified	Not reported
MLCR-AAArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Share of tasks judged accurate, complete, and concise · Expert + compound (hard) sets · Benchmark developed by Wisedocs · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-18.	Not reported	16.11% Reported settings Kimi K2.7 Code; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-7-code; Mode from evaluator isReasoning metadata; effort budget not specified	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	-10.22 Reported settings Kimi K2.7 Code; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-7-code; Mode from evaluator isReasoning metadata; effort budget not specified	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	39.57% Reported settings Kimi K2.7 Code; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-7-code; Mode from evaluator isReasoning metadata; effort budget not specified	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	47.8% Reported settings Kimi K2.7 Code; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-7-code; Mode from evaluator isReasoning metadata; effort budget not specified	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	90.06% Reported settings Kimi K2.7 Code; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-7-code; Mode from evaluator isReasoning metadata; effort budget not specified	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	20.21% Reported settings Kimi K2.7 Code; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-7-code; Mode from evaluator isReasoning metadata; effort budget not specified	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	44.7% Reported settings Kimi K2.7 Code; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-7-code; Mode from evaluator isReasoning metadata; effort budget not specified	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	67.42% Reported settings Kimi K2.7 Code; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-7-code; Mode from evaluator isReasoning metadata; effort budget not specified	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	1.01% Reported settings Kimi K2.7 Code; Reported effort: reasoning; Model source: https://artificialanalysis.ai/models/kimi-k2-7-code; Mode from evaluator isReasoning metadata; effort budget not specified	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	14% Reported settings Epoch AI Inspect; task 2.0.0; scorer exact; model=kimi-k2.7-code; run=bSyTSKD8RiRNZCGNu6MnFp; 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	12.2% Reported settings Epoch AI Inspect; task 2.0.0; scorer verification_code; model=kimi-k2.7-code; run=UTVSgirxQpTgmTHbgE9EUk; 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	54.04% Reported settings Epoch AI Inspect; task 2.0.0; scorer verification_code; model=kimi-k2.7-code; run=X3RxRkt2pBUXYJjAQHsUo6; mean accuracy; https://epoch.ai/data/benchmarks.csv
Epoch · GPQA diamond · v1.0.11Epoch AI · Epoch AI Inspect; task 1.0.11; 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	87.88% Reported settings Epoch AI Inspect; task 1.0.11; scorer choice; model=kimi-k2.7-code; run=XneEig6pACkAWeekvgCwNk; mean accuracy; https://epoch.ai/data/benchmarks.csv
Epoch · OTIS Mock AIME 2024-2025 · v1.1.6Epoch AI · Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match 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	95.56% Reported settings Epoch AI Inspect; task 1.1.6; scorer model_extracted_exact_match; model=kimi-k2.7-code; run=ENc5ZM5TpBYNKkTWN4xyQM; mean accuracy; https://epoch.ai/data/benchmarks.csv
Epoch · SimpleQA Verified · v1.2.0Epoch AI · Epoch AI Inspect; task 1.2.0; scorer simpleqa_scorer 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	36.5% Reported settings Epoch AI Inspect; task 1.2.0; scorer simpleqa_scorer; model=kimi-k2.7-code; run=5AijYw5bFJtSuahnbzNo6Z; 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 · 8,915 results across 259 models · Collected 2026-10-18

Kimi-K2.7-Code · Reasoning

Compare with

One configuration, seven capabilities

Agentic

Hard reasoning

Coding

Human pref

Knowledge

Multimodal

Long context

Capability score evidence

Benchmark results