RankingEffort benchmarks
Kimi-K2.6
46 measured results · 4 effort settings · 38 benchmark/harness combinations
Change model
Capability profile
One configuration, seven capabilities
- AKimi-K2.6 · Reasoning4 of 7 capabilities supported
Gaps are unknown, not zero. Hollow points are preliminary.
Agentic
A29.0SupportedHard reasoning
A38.0SupportedCoding
A32.3SupportedHuman pref
UnknownKnowledge
A46.0PreliminaryMultimodal
A36.6SupportedLong context
A45.6Preliminary
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: 24.6 overall comparison score. Meets the overall evidence requirements.
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 · 12.2% direct comparison weight
- Terminal-Bench · 11.9% direct comparison weight
- CharXiv · 6.3% direct comparison weight
- SWE-bench Multilingual · 6.3% direct comparison weight
- GDPval · 5.6% direct comparison weight
- Other families (12) · 57.8% 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 2026-11-22.
Both ranks use the same surviving configurations for each removal. The cohort starts with 602 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.
| Removed source | Rank before → after | Rank movement | Cohort remaining / lost support | Score after (change) |
|---|---|---|---|---|
| Artificial Analysis | Comparison support lost; no rank | 230 remaining / 372 lost | Unavailable | |
| ARC Prize | 180 → 182 | Down 2 | 602 remaining / 0 lost | 27.8 |
| Datacurve | 180 → 175 | Up 5 | 602 remaining / 0 lost | 22.7 |
| LiveCodeBench | 180 → 180 | No movement | 602 remaining / 0 lost | 24.5 |
| Scale | 180 → 184 | Down 4 | 602 remaining / 0 lost | 25.4 |
| Terminal-Bench | 180 → 178 | Up 2 | 602 remaining / 0 lost | 25.0 |
| Cognition | 180 → 179 | Up 1 | 602 remaining / 0 lost | 23.7 |
| LiveBench | 179 → 182 | Down 3 | 601 remaining / 1 lost | 24.5 |
| SWE-rebench | 180 → 180 | No movement | 602 remaining / 0 lost | 24.7 |
| Epoch AI | 177 → 181 | Down 4 | 588 remaining / 14 lost | 24.3 |
| Vals AI | 180 → 180 | No movement | 601 remaining / 1 lost | 24.4 |
| Provider reports · Anthropic | 180 → 180 | No movement | 602 remaining / 0 lost | 24.6 |
| Provider reports · Moonshot AI | 180 → 184 | Down 4 | 602 remaining / 0 lost | 22.4 |
| Provider reports · Meta | 180 → 180 | No movement | 602 remaining / 0 lost | 24.6 |
| Provider reports · Mistral | 180 → 180 | No movement | 602 remaining / 0 lost | 24.6 |
| Provider reports · OpenAI | 180 → 182 | Down 2 | 602 remaining / 0 lost | 24.7 |
| All provider reports | 180 → 184 | Down 4 | 602 remaining / 0 lost | 22.5 |
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 | 20.1 | -4.5 |
| mmmu-pro | 28.2 | +3.6 |
| arc-agi | 27.1 | +2.5 |
| deepswe | 22.7 | -1.8 |
| frontiercode | 23.7 | -0.9 |
| briefcase | 25.4 | +0.8 |
| automationbench | 25.4 | +0.8 |
| itbench | 25.4 | +0.8 |
| apex-agents | 23.9 | -0.7 |
| gpqa | 23.9 | -0.6 |
| aa-lcr | 23.9 | -0.6 |
| ifbench | 24.1 | -0.5 |
| epoch-game-puzzles | 24.2 | -0.4 |
| gdpval | 25.0 | +0.4 |
| simpleqa | 25.0 | +0.4 |
| tau-bench | 24.3 | -0.3 |
| enterprise-ops | 24.3 | -0.3 |
| terminal-bench-science | 24.8 | +0.2 |
| enigma-eval | 24.8 | +0.2 |
| mmlu-pro | 24.8 | +0.2 |
| arc-agi-3 | 24.4 | -0.2 |
| omniscience | 24.8 | +0.2 |
| hle | 24.4 | -0.2 |
| multi-swe-bench | 24.4 | -0.1 |
| livebench-instructions | 24.7 | +0.1 |
| swe-atlas-qna | 24.5 | -0.1 |
| livebench-language | 24.7 | +0.1 |
| analyst-agent | 24.7 | +0.1 |
| swe-rebench | 24.7 | +0.1 |
| vals-finance-agent | 24.5 | -0.1 |
| vals-legal-research | 24.5 | -0.1 |
| livebench-data | 24.5 | -0.1 |
| gmmlu | 24.6 | +0.1 |
| swe-atlas-test-writing | 24.5 | -0.1 |
| vals-tax-agent | 24.5 | -0.1 |
| livebench-reasoning | 24.5 | -0.0 |
| livebench-math | 24.6 | +0.0 |
| swe-atlas-refactoring | 24.5 | -0.0 |
| vibe-code | 24.5 | -0.0 |
| aime | 24.6 | +0.0 |
| livecodebench | 24.6 | +0.0 |
| vals-excel-modeling | 24.6 | -0.0 |
| math500 | 24.6 | +0.0 |
| frontiermath | 24.6 | +0.0 |
| vals-code-migration | 24.6 | -0.0 |
| harvey | 24.6 | -0.0 |
| critpt | 24.6 | +0.0 |
| swe-bench-pro | 24.6 | +0.0 |
| gdp-pdf | 24.6 | -0.0 |
| livebench-coding | 24.6 | -0.0 |
What evidence is missing from the fit?
Across all collected settings for this model: 135 observations, 31 contributing, 0 matched without graph weight and 104 excluded. Counts do not establish rank eligibility.
- 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
- 17 · 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.
Benchmark results
Reviewed retained observations are in use. October 2026 Real-SWE board has no 95% confidence whisker, so these scores stay at the 2026-10-18 retrieval. Original source retrieval 2026-10-18; source updated 2026-10-18.
| Benchmark / source | High | Reasoning | Non-reasoning | Unspecified |
|---|---|---|---|---|
AA-Briefcase EloBenchmark detailsAA-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 2026-11-22. | Not reported | 820.7 Elo Reported settingsKimi 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-AABenchmark detailsIndependently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-11-22. | Not reported | 28.47% Reported settingsKimi 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 v1.1Benchmark detailsIndependently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-11-22. | Not reported | 81% Reported settingsKimi 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 settingsKimi K2.6 (Non-reasoning); Model source: https://artificialanalysis.ai/models/kimi-k2-6-non-reasoning | Not reported |
AutomationBench-AABenchmark detailsShare 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 2026-11-22. | Not reported | 13.02% Reported settingsKimi 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 |
CritPtBenchmark detailsBenchmark developed by Argonne and UIUC, with contributions from 60+ researchers globally · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-11-22. | Not reported | 8% Reported settingsKimi 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 settingsKimi K2.6 (Non-reasoning); Model source: https://artificialanalysis.ai/models/kimi-k2-6-non-reasoning | Not reported |
EnterpriseOps-Gym-AABenchmark detailsOverall 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 2026-11-22. | Not reported | 38.53% Reported settingsKimi 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 RateBenchmark detailsShare of attempts where every atomic criterion passed · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-11-22. | Not reported | 13% Reported settingsKimi 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 LeaderboardBenchmark detailsElo 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 2026-11-22. | Not reported | 1,046.37 Elo Reported settingsKimi 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 DiamondBenchmark detailsIndependently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-11-22. | Not reported | 91.11% Reported settingsKimi 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 settingsKimi K2.6 (Non-reasoning); Model source: https://artificialanalysis.ai/models/kimi-k2-6-non-reasoning | Not reported |
Humanity's Last ExamBenchmark detailsIndependently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-11-22. | Not reported | 37.49% Reported settingsKimi 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 settingsKimi K2.6 (Non-reasoning); Model source: https://artificialanalysis.ai/models/kimi-k2-6-non-reasoning | Not reported |
IFBenchBenchmark detailsIndependently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-11-22. | Not reported | 75.99% Reported settingsKimi 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 settingsKimi K2.6 (Non-reasoning); Model source: https://artificialanalysis.ai/models/kimi-k2-6-non-reasoning | Not reported |
ITBench-AABenchmark detailsCombined public and private Site Reliability Engineering (SRE) tasks · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-11-22. | Not reported | 31.19% Reported settingsKimi 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 |
MLCR-AABenchmark detailsShare of responses judged complete with no claim contradicting the record · Expert + compound (hard) sets · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-11-22. | Not reported | 11.11% Reported settingsKimi 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-ProBenchmark detailsIndependently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-11-22. | Not reported | 79.36% Reported settingsKimi 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 |
SciCodeBenchmark detailsBenchmark 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 2026-11-22. | Not reported | 51.5% Reported settingsKimi 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 TelecomBenchmark detailsIndependently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-11-22. | Not reported | 95.91% Reported settingsKimi 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 settingsKimi K2.6 (Non-reasoning); Model source: https://artificialanalysis.ai/models/kimi-k2-6-non-reasoning | Not reported |
𝜏³-BankingBenchmark detailsBenchmark developed by Sierra Research · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-11-22. | Not reported | 23.3% Reported settingsKimi 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 HardBenchmark detailsIndependently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-11-22. | Not reported | 43.94% Reported settingsKimi 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 settingsKimi K2.6 (Non-reasoning); Model source: https://artificialanalysis.ai/models/kimi-k2-6-non-reasoning | Not reported |
Terminal-Bench v2.1Benchmark detailsBenchmark 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 2026-11-22. | Not reported | 65.92% Reported settingsKimi 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 v4.0Benchmark detailsBenchmark 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 2026-11-22. | Not reported | 0.51% Reported settingsKimi 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 · v2.0.0Benchmark detailsEpoch 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 2026-11-22. | Not reported | Not reported | Not reported | 20% Reported settingsEpoch 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 · v2.0.0Benchmark detailsEpoch 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 2026-11-22. | Not reported | Not reported | Not reported | 25.64% Reported settingsEpoch 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 · v2.0.0Benchmark detailsEpoch 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 2026-11-22. | Not reported | Not reported | Not reported | 57.19% Reported settingsEpoch 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 · v1.0.8Benchmark detailsEpoch 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 2026-11-22. | Not reported | Not reported | Not reported | 90.78% Reported settingsEpoch AI Inspect; task 1.0.8; scorer choice; model=kimi-k2.6; run=LjgJoDosTLkiGVT59smA7q; mean accuracy; https://epoch.ai/data/benchmarks.csv |
Epoch · Mystery Game Puzzles · v1.0.4 · Tool submissionBenchmark detailsEpoch 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 2026-11-22. | Not reported | Not reported | 12% Reported settingsEpoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=kimi-k2.6_none; run=8iiRQiAoCepDELQfUv3VDq; mean accuracy; https://epoch.ai/data/benchmarks.csv | 18% Reported settingsEpoch AI Inspect; task 1.0.4; scorer agent_submitted_next_move_scorer; model=kimi-k2.6; run=RA5MRbmWJpFPR29BQxfvZt; 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 · 10,184 results across 381 models · Collected 2026-11-22