# Kimi K2.6 > Source: Benchize (https://benchize.com) — https://benchize.com/models/kimi-k2-6. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/kimi-k2-6. Moonshot AI Canonical URL: https://benchize.com/models/kimi-k2-6 Last updated: Thu, 22 Oct 2026 06:20:09 GMT Reproduction and quotation must name Benchize, link to the canonical HTML URL, and retain individual source citations. Moonshot AI ## Benchmarks | Benchmark | Score | ± | Rank | Cost | Source | | | --- | --- | --- | --- | --- | --- | --- | | [Judgemark v4](https://benchize.com/benchmarks/eq-bench%3Ajudgemark-v4.md) | 57.26% | CI 54.76–63.32% | 20 / 38 | — | [eq bench · judgemark-v4](https://eqbench.com/judgemark-v4.js) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.572626 \| score_fraction \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol judgemark-v4 sourceModelVersion moonshotai/Kimi-K2.6 ### Reported statistics Uncertainty Confidence interval: 54.76–63.32% confidenceIntervalHigh 0.633247 confidenceIntervalLow 0.547558 ### Source [Original source](https://eqbench.com/judgemark-v4.js) Source eq bench Original model label moonshotai/Kimi-K2.6 Source version judgemark-v4 Observed 2026-10-22T05:10:06.884Z Evidence SHA-256 `2b0d42aef4f614dd199dc38399be7b88075a919db52020c3759f190defc92a4d` Source locator `/leaderboardDataJudgemarkV4/21` | | | | | | | | [Creative Writing v3](https://benchize.com/benchmarks/eq-bench%3Acreative-writing-v3.md) | 1,724.5elo | — | 28 / 90 | — | [eq bench · creative-writing-v3](https://eqbench.com/creative_writing.js) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1724.5 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 16.67 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion moonshotai/Kimi-K2.6 ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label moonshotai/Kimi-K2.6 Source version creative-writing-v3 Observed 2026-10-22T05:10:05.433Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/30` | | | | | | | | [PerceptionBench](https://benchize.com/benchmarks/perceptionbench.md) | 42.6% | — | 9 / 14 | — | [Moonshot AI / PerceptionBench · ba032c06e9b6ee3679171ff6ba643b7a0cfebe2e](https://github.com/MoonshotAI/PerceptionBench) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 42.6 \| percent \| overall \| Higher is better \| \| `visual_relation_accuracy` \| 50.9 \| percent \| atomic_capability \| Higher is better \| \| `counting_accuracy` \| 45.2 \| percent \| atomic_capability \| Higher is better \| \| `attribute_accuracy` \| 43.6 \| percent \| atomic_capability \| Higher is better \| \| `depth_3d_accuracy` \| 42.4 \| percent \| atomic_capability \| Higher is better \| \| `localization_accuracy` \| 45.2 \| percent \| atomic_capability \| Higher is better \| \| `comparison_accuracy` \| 39.1 \| percent \| atomic_capability \| Higher is better \| \| `fine_grained_recognition_accuracy` \| 34.5 \| percent \| atomic_capability \| Higher is better \| \| `contextual_integration_accuracy` \| 40.4 \| percent \| atomic_capability \| Higher is better \| \| `ocr_accuracy` \| 40.8 \| percent \| atomic_capability \| Higher is better \| \| `hallucination_accuracy` \| 41.0 \| percent \| atomic_capability \| Higher is better \| ### Configuration judgeModel gpt-oss-120b promptProtocol unified reasoningBudgetPolicy highest_available ### Reported statistics sampleSize 3000 ### Source Score publisher [Moonshot AI / PerceptionBench](https://github.com/MoonshotAI/PerceptionBench) Collected via [perceptionbench](https://api.github.com/repos/MoonshotAI/PerceptionBench/contents/README.md?ref=ba032c06e9b6ee3679171ff6ba643b7a0cfebe2e) Publisher reference Referenced by the collection source; the upstream result has not been independently captured. Benchmark [https://api.github.com/repos/MoonshotAI/PerceptionBench/contents/README.md?ref=ba032c06e9b6ee3679171ff6ba643b7a0cfebe2e](https://api.github.com/repos/MoonshotAI/PerceptionBench/contents/README.md?ref=ba032c06e9b6ee3679171ff6ba643b7a0cfebe2e) [Collected via](https://api.github.com/repos/MoonshotAI/PerceptionBench/contents/README.md?ref=ba032c06e9b6ee3679171ff6ba643b7a0cfebe2e) Source Moonshot AI / PerceptionBench Original model label Kimi K2.6 Source version ba032c06e9b6ee3679171ff6ba643b7a0cfebe2e Observed 2026-10-21T16:33:36.858Z Evidence SHA-256 `0863d20bc397e2324ea76099fe703aed419dc7f0dbb359e522f7dac07dda6529` Source locator `/leaderboard/rows/10` | | | | | | | | [AutomationBench](https://benchize.com/benchmarks/zapier%3Aautomationbench.md) | 2.59% | — | 98 / 113 | $0.28 | [zapier](https://framerusercontent.com/sites/4WTSl4BNjd1q9QFEFibC6h/lOvLnhItj8S8-1vyjH_s33Jn-WmUXPmiJ5Diajl0Q38.CMutaHYl.mjs) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 2.59 \| percent \| reported \| Higher is better \| \| `cost` \| 0.28 \| USD \| per_task \| Lower is better \| ### Configuration benchmarkVersion 1.0.6 costFootnote false Fallback policy Not reported Reasoning effort unknown Model configuration Kimi K2.6 thinkingEnabled Not reported ### Reported statistics rank 111 ### Source [Original source](https://framerusercontent.com/sites/4WTSl4BNjd1q9QFEFibC6h/lOvLnhItj8S8-1vyjH_s33Jn-WmUXPmiJ5Diajl0Q38.CMutaHYl.mjs) Source zapier Original model label Kimi K2.6 Observed 2026-10-21T16:34:56.783Z Evidence SHA-256 `43978e38f018789fa59c11de5328abe9e5905bfa9a5a4d601fa3aa4d9c153b0d` Source locator `/rows/110` | | | | | | | | [Short Story Writing — Pairwise Comparison](https://benchize.com/benchmarks/lechmazur-short-story%3Apairwise.md) | 0.08 | 95% CI -0.03–0.19 | 30 / 50 | — | [lechmazur short story · 8ba548d1cffefa5c472d3832e05f64e119a88fa4](https://api.github.com/repos/lechmazur/writing/contents/data/writing_gemini_argon_20261013/ratings.csv?ref=8ba548d1cffefa5c472d3832e05f64e119a88fa4) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `thurstone_rating` \| 0.07844723446558423 \| index \| pooled_observed_panel \| Higher is better \| \| `win_probability` \| 0.5115378923409997 \| score_fraction \| comparison_pool \| Higher is better \| ### Configuration benchmarkScope data/writing_gemini_argon_20261013 ### Reported statistics Uncertainty 95% confidence interval: -0.03–0.19 bootstrapSamples 300 confidenceInterval95 ["-0.026638259912426777","0.1929822243811043"] sourceRank 30 ### Source [Original source](https://api.github.com/repos/lechmazur/writing/contents/data/writing_gemini_argon_20261013/ratings.csv?ref=8ba548d1cffefa5c472d3832e05f64e119a88fa4) Source lechmazur short story Original model label Kimi K2.6 Source version 8ba548d1cffefa5c472d3832e05f64e119a88fa4 Observed 2026-10-21T16:34:21.130Z Evidence SHA-256 `c36baebed9f302ff7ad8fe97907d72e1757a015a39b6a3b23437597cf8e3bff6` Source locator `/rows/29` | | | | | | | | [Vending-Bench 2](https://benchize.com/benchmarks/vendingbench%3Av2.md) | — | — | — | $6,204.57 | [vendingbench](https://andonlabs.com/_app/immutable/chunks/Cjn0_qj9.js) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `final_balance` \| 6204.570000000001 \| USD \| one_simulated_year \| Higher is better \| \| `geometric_mean_balance` \| 6029.829477515791 \| USD \| positive_final_balances \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Kimi K2.6 thinkingEnabled Not reported ### Reported statistics confidenceHalfWidth95 1295.3069183909802 positiveBalanceRuns 5 runCount 5 standardDeviation 1477.7522047183695 standardError 660.8708767300919 ### Source [Original source](https://andonlabs.com/_app/immutable/chunks/Cjn0_qj9.js) Source vendingbench Original model label Kimi K2.6 Observed 2026-10-21T16:36:40.592Z Evidence SHA-256 `1a0b043147050298c405bcb743d73e425d532464202231cd18c27f836fa5f223` Source locator `/rows/54` | | | | | | | | [EQ-Bench 4](https://benchize.com/benchmarks/eq-bench%3Aeqbench4.md) | 1,201.6elo | CI 1,192.8–1,210.1 | 17 / 26 | — | [eq bench · eqbench4](https://eqbench.com/eqbench4/eqbench4_data.js) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1201.6 \| elo \| overall \| Higher is better \| ### Configuration protocol eqbench4 ### Reported statistics Uncertainty Confidence interval: 1,192.8–1,210.1 confidenceIntervalHigh 1210.1 confidenceIntervalLow 1192.8 scenarios 120 ### Source [Original source](https://eqbench.com/eqbench4/eqbench4_data.js) Source eq bench Original model label kimi-k2.6 Source version eqbench4 Observed 2026-10-22T05:10:04.699Z Evidence SHA-256 `188d8ea4a393978063a6c24dff6c92ce185169827038bfa558091212a68c29d8` Source locator `/models/16` | | | | | | | | [Long-Horizon Terminal-Bench](https://benchize.com/benchmarks/lhtb%3Aoverall.md) | 25.5% | — | 17 / 19 | $9.94 | [lhtb](https://zli12321.github.io/LHTB/script.js) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `mean_reward` \| 0.255 \| score_fraction \| reported \| Higher is better \| \| `solved_count` \| 0 \| tasks \| reward_gte_0_95 \| Higher is better \| \| `cost_per_task` \| 9.94 \| USD \| per_task \| Lower is better \| ### Configuration harness official_common_harness Reasoning effort unknown reportOrigin paper ### Reported statistics sampleSize 46 sourceThresholdCounts Not reported ### Source [Original source](https://zli12321.github.io/LHTB/script.js) Source lhtb Original model label Kimi K2.6 Observed 2026-10-22T05:00:05.057Z Evidence SHA-256 `8b9c27664cc6298fa234c607ca27c953ec91b2eb9d116b8530cfaaa6722fa39e` Source locator `/rows/18` | | | | | | | | [NC Bench](https://benchize.com/benchmarks/nc-bench%3Aoverall.md) | 92.57% | — | 31 / 144 | — | [nc bench](https://www.nc-bench.com/models) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 92.57 \| percent \| reported \| Higher is better \| \| `tooling` \| 99.81 \| percent \| category \| Higher is better \| \| `creative_writing` \| 85.47 \| percent \| category \| Higher is better \| \| `language` \| 96.77 \| percent \| category \| Higher is better \| \| `utility` \| 97.42 \| percent \| category \| Higher is better \| \| `reasoning` \| 91.69 \| percent \| category \| Higher is better \| \| `text_editing` \| 98 \| percent \| category \| Higher is better \| \| `rule_following` \| 76.94 \| percent \| category \| Higher is better \| \| `hallucination` \| 94.43 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Kimi K2.6 thinkingEnabled Not reported ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Kimi K2.6 Observed 2026-10-22T06:10:03.426Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/38` | | | | | | | | [EQ-Bench 3](https://benchize.com/benchmarks/eq-bench%3Aeqbench3.md) | 1,561.2elo | CI 1,528.8–1,593.6 | 10 / 50 | — | [eq bench · eqbench3](https://eqbench.com/eqbench3.js) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_norm` \| 1561.2 \| elo \| overall \| Higher is better \| \| `rubric_0_100` \| 76.6 \| percent \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol eqbench3 sourceModelVersion moonshotai/Kimi-K2.6 ### Reported statistics Uncertainty Confidence interval: 1,528.8–1,593.6 confidenceIntervalHigh 1593.6 confidenceIntervalLow 1528.8 ### Source [Original source](https://eqbench.com/eqbench3.js) Source eq bench Original model label moonshotai/Kimi-K2.6 Source version eqbench3 Observed 2026-10-22T05:10:04.922Z Evidence SHA-256 `3672ff093e739f07ff664a2e6013bc38a6977a146e4092b4cef80ba1780542b2` Source locator `/leaderboardDataEQBench3/12` | | | | | | | | [Longform Creative Writing](https://benchize.com/benchmarks/eq-bench%3Alongform-writing.md) | 78.5% | — | 17 / 93 | — | [eq bench · longform-writing](https://eqbench.com/creative_writing_longform.js) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `overall_score_100` \| 78.5 \| percent \| overall \| Higher is better \| \| `chapter1_avg` \| 16.26 \| rubric_score \| overall \| Higher is better \| \| `chapter2_avg` \| 16.34 \| rubric_score \| overall \| Higher is better \| \| `chapter3_avg` \| 16.67 \| rubric_score \| overall \| Higher is better \| \| `chapter4_avg` \| 16.49 \| rubric_score \| overall \| Higher is better \| \| `chapter5_avg` \| 16.33 \| rubric_score \| overall \| Higher is better \| \| `chapter6_avg` \| 16.40 \| rubric_score \| overall \| Higher is better \| \| `chapter7_avg` \| 16.14 \| rubric_score \| overall \| Higher is better \| \| `chapter8_avg` \| 16.32 \| rubric_score \| overall \| Higher is better \| \| `final_judgement_avg` \| 15.61 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol longform-writing sourceModelVersion moonshotai/Kimi-K2.6 ### Source [Original source](https://eqbench.com/creative_writing_longform.js) Source eq bench Original model label moonshotai/Kimi-K2.6 Source version longform-writing Observed 2026-10-22T05:10:05.903Z Evidence SHA-256 `3ba283ce357ac7620e16db640a961879c30fe3ddc50a27de9a8ed4290784825c` Source locator `/leaderboardDataLongformV3/110` | | | | | | | | [SVGBench Arena](https://benchize.com/benchmarks/svgbench%3Aarena.md) | 1,570 | — | 43 / 191 | — | [svgbench](https://svgbench.ai/api/leaderboard?shape=2) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1570 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_moonshotai_kimi_k2_6 ### Reported statistics coverageCount 27 draws 3 judged 106 losses 47 rank 53 ratingDeviation 28 wins 56 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label Kimi K2.6 Observed 2026-10-22T04:30:04.538Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/51` | | | | | | | --- Cite as: Kimi K2.6 — Benchize, https://benchize.com/models/kimi-k2-6 (retrieved 2026-10-22)