# Kimi K3 > Source: Benchize (https://benchize.com) — https://benchize.com/models/kimi-k3. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/kimi-k3. MoonshotAI Canonical URL: https://benchize.com/models/kimi-k3 Last updated: Wed, 21 Oct 2026 18:52:20 GMT Reproduction and quotation must name Benchize, link to the canonical HTML URL, and retain individual source citations. MoonshotAI ## Benchmarks | Benchmark | Score | ± | Rank | Cost | Source | | | --- | --- | --- | --- | --- | --- | --- | | [EQ-Bench 4](https://benchize.com/benchmarks/eq-bench%3Aeqbench4.md) | 1,339.3elo | CI 1,325–1,355.5 | 3 / 26 | — | [eq bench · eqbench4](https://eqbench.com/eqbench4/eqbench4_data.js) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1339.3 \| elo \| overall \| Higher is better \| ### Configuration protocol eqbench4 ### Reported statistics Uncertainty Confidence interval: 1,325–1,355.5 confidenceIntervalHigh 1355.5 confidenceIntervalLow 1325 scenarios 120 ### Source [Original source](https://eqbench.com/eqbench4/eqbench4_data.js) Source eq bench Original model label kimi-k3 Source version eqbench4 Observed 2026-10-21T16:35:00.261Z Evidence SHA-256 `188d8ea4a393978063a6c24dff6c92ce185169827038bfa558091212a68c29d8` Source locator `/models/2` | | | | | | | | [AutomationBench](https://benchize.com/benchmarks/zapier%3Aautomationbench.md) | 22.68% | — | 33 / 113 | $0.43 | [zapier](https://framerusercontent.com/sites/4WTSl4BNjd1q9QFEFibC6h/lOvLnhItj8S8-1vyjH_s33Jn-WmUXPmiJ5Diajl0Q38.CMutaHYl.mjs) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 22.68 \| percent \| reported \| Higher is better \| \| `cost` \| 0.43 \| USD \| per_task \| Lower is better \| ### Configuration benchmarkVersion 1.0.6 costFootnote false Fallback policy Not reported Reasoning effort unknown Model configuration Kimi K3 thinkingEnabled Not reported ### Reported statistics rank 33 ### Source [Original source](https://framerusercontent.com/sites/4WTSl4BNjd1q9QFEFibC6h/lOvLnhItj8S8-1vyjH_s33Jn-WmUXPmiJ5Diajl0Q38.CMutaHYl.mjs) Source zapier Original model label Kimi K3 Observed 2026-10-21T16:34:56.783Z Evidence SHA-256 `43978e38f018789fa59c11de5328abe9e5905bfa9a5a4d601fa3aa4d9c153b0d` Source locator `/rows/32` | | | | | | | | [Creative Writing v3](https://benchize.com/benchmarks/eq-bench%3Acreative-writing-v3.md) | 2,082.3elo | — | 5 / 90 | — | [eq bench · creative-writing-v3](https://eqbench.com/creative_writing.js) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 2082.3 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 16.85 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion kimi-k3 ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label kimi-k3 Source version creative-writing-v3 Observed 2026-10-21T16:35:01.421Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/4` | | | | | | | | [Longform Creative Writing](https://benchize.com/benchmarks/eq-bench%3Alongform-writing.md) | 79.6% | — | 16 / 93 | — | [eq bench · longform-writing](https://eqbench.com/creative_writing_longform.js) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `overall_score_100` \| 79.6 \| percent \| overall \| Higher is better \| \| `chapter1_avg` \| 17.02 \| rubric_score \| overall \| Higher is better \| \| `chapter2_avg` \| 16.77 \| rubric_score \| overall \| Higher is better \| \| `chapter3_avg` \| 16.56 \| rubric_score \| overall \| Higher is better \| \| `chapter4_avg` \| 16.61 \| rubric_score \| overall \| Higher is better \| \| `chapter5_avg` \| 16.63 \| rubric_score \| overall \| Higher is better \| \| `chapter6_avg` \| 16.29 \| rubric_score \| overall \| Higher is better \| \| `chapter7_avg` \| 16.20 \| rubric_score \| overall \| Higher is better \| \| `chapter8_avg` \| 16.20 \| rubric_score \| overall \| Higher is better \| \| `final_judgement_avg` \| 16.55 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol longform-writing sourceModelVersion kimi-k3 ### Source [Original source](https://eqbench.com/creative_writing_longform.js) Source eq bench Original model label kimi-k3 Source version longform-writing Observed 2026-10-21T16:35:02.575Z Evidence SHA-256 `3ba283ce357ac7620e16db640a961879c30fe3ddc50a27de9a8ed4290784825c` Source locator `/leaderboardDataLongformV3/122` | | | | | | | | [PerceptionBench](https://benchize.com/benchmarks/perceptionbench.md) | 58.5% | — | 2 / 14 | — | [Moonshot AI / PerceptionBench · ba032c06e9b6ee3679171ff6ba643b7a0cfebe2e](https://github.com/MoonshotAI/PerceptionBench) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 58.5 \| percent \| overall \| Higher is better \| \| `visual_relation_accuracy` \| 68.2 \| percent \| atomic_capability \| Higher is better \| \| `counting_accuracy` \| 59.7 \| percent \| atomic_capability \| Higher is better \| \| `attribute_accuracy` \| 59.4 \| percent \| atomic_capability \| Higher is better \| \| `depth_3d_accuracy` \| 52.4 \| percent \| atomic_capability \| Higher is better \| \| `localization_accuracy` \| 70.3 \| percent \| atomic_capability \| Higher is better \| \| `comparison_accuracy` \| 59.1 \| percent \| atomic_capability \| Higher is better \| \| `fine_grained_recognition_accuracy` \| 55.9 \| percent \| atomic_capability \| Higher is better \| \| `contextual_integration_accuracy` \| 53.3 \| percent \| atomic_capability \| Higher is better \| \| `ocr_accuracy` \| 61.2 \| percent \| atomic_capability \| Higher is better \| \| `hallucination_accuracy` \| 41.7 \| 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 K3 Source version ba032c06e9b6ee3679171ff6ba643b7a0cfebe2e Observed 2026-10-21T16:33:36.858Z Evidence SHA-256 `0863d20bc397e2324ea76099fe703aed419dc7f0dbb359e522f7dac07dda6529` Source locator `/leaderboard/rows/1` | | | | | | | | [Short Story Writing — Pairwise Comparison](https://benchize.com/benchmarks/lechmazur-short-story%3Apairwise.md) | 2.42 | 95% CI 2.34–2.5 | 10 / 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` \| 2.41992507841589 \| index \| pooled_observed_panel \| Higher is better \| \| `win_probability` \| 0.8227285609736585 \| score_fraction \| comparison_pool \| Higher is better \| ### Configuration benchmarkScope data/writing_gemini_argon_20261013 ### Reported statistics Uncertainty 95% confidence interval: 2.34–2.5 bootstrapSamples 300 confidenceInterval95 ["2.342189338415047","2.5014128352949645"] sourceRank 10 ### 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 K3 Source version 8ba548d1cffefa5c472d3832e05f64e119a88fa4 Observed 2026-10-21T16:34:21.130Z Evidence SHA-256 `c36baebed9f302ff7ad8fe97907d72e1757a015a39b6a3b23437597cf8e3bff6` Source locator `/rows/9` | | | | | | | --- Cite as: Kimi K3 — Benchize, https://benchize.com/models/kimi-k3 (retrieved 2026-10-21)