# Kimi K2.5

> Source: Benchize (https://benchize.com) — https://benchize.com/models/kimi-k2-5. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/kimi-k2-5.

Moonshot AI

Canonical URL: https://benchize.com/models/kimi-k2-5
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 |  |
| --- | --- | --- | --- | --- | --- | --- |
| [NC Bench](https://benchize.com/benchmarks/nc-bench%3Aoverall.md) | 90.86% | — | 50 / 144 | — | [nc bench](https://www.nc-bench.com/models) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 90.86 \| percent \| reported \| Higher is better \| \| `tooling` \| 100 \| percent \| category \| Higher is better \| \| `creative_writing` \| 81.35 \| percent \| category \| Higher is better \| \| `language` \| 97.1 \| percent \| category \| Higher is better \| \| `utility` \| 96.63 \| percent \| category \| Higher is better \| \| `reasoning` \| 87.99 \| percent \| category \| Higher is better \| \| `text_editing` \| 97.79 \| percent \| category \| Higher is better \| \| `rule_following` \| 72.03 \| percent \| category \| Higher is better \| \| `hallucination` \| 94.01 \| percent \| category \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Kimi K2.5 thinkingEnabled Not reported ### Source [Original source](https://www.nc-bench.com/models) Source nc bench Original model label Kimi K2.5 Observed 2026-10-22T06:10:03.426Z Evidence SHA-256 `ec261022458543624b08a136d01f5a2f0666cd52ffb49c64d6ca983e8543d1b5` Source locator `/rows/61` |  |  |  |  |  |  |
| [Longform Creative Writing](https://benchize.com/benchmarks/eq-bench%3Alongform-writing.md) | 74.9% | — | 26 / 93 | — | [eq bench · longform-writing](https://eqbench.com/creative_writing_longform.js) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `overall_score_100` \| 74.9 \| percent \| overall \| Higher is better \| \| `chapter1_avg` \| 16.13 \| rubric_score \| overall \| Higher is better \| \| `chapter2_avg` \| 16.13 \| rubric_score \| overall \| Higher is better \| \| `chapter3_avg` \| 16.13 \| rubric_score \| overall \| Higher is better \| \| `chapter4_avg` \| 15.81 \| rubric_score \| overall \| Higher is better \| \| `chapter5_avg` \| 15.71 \| rubric_score \| overall \| Higher is better \| \| `chapter6_avg` \| 15.35 \| rubric_score \| overall \| Higher is better \| \| `chapter7_avg` \| 15.57 \| rubric_score \| overall \| Higher is better \| \| `chapter8_avg` \| 15.54 \| rubric_score \| overall \| Higher is better \| \| `final_judgement_avg` \| 14.29 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol longform-writing sourceModelVersion moonshotai/Kimi-K2.5 ### Source [Original source](https://eqbench.com/creative_writing_longform.js) Source eq bench Original model label moonshotai/Kimi-K2.5 Source version longform-writing Observed 2026-10-22T05:10:05.903Z Evidence SHA-256 `3ba283ce357ac7620e16db640a961879c30fe3ddc50a27de9a8ed4290784825c` Source locator `/leaderboardDataLongformV3/2` |  |  |  |  |  |  |
| [Vending-Bench 2](https://benchize.com/benchmarks/vendingbench%3Av2.md) | — | — | — | $1,198.46 | [vendingbench](https://andonlabs.com/_app/immutable/chunks/Cjn0_qj9.js) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `final_balance` \| 1198.4579999999999 \| USD \| one_simulated_year \| Higher is better \| \| `geometric_mean_balance` \| 1117.8576238170353 \| USD \| positive_final_balances \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration Kimi K2.5 thinkingEnabled Not reported ### Reported statistics confidenceHalfWidth95 1169.5262199631259 positiveBalanceRuns 4 runCount 5 standardDeviation 1334.2551680132249 standardError 596.6970510015948 ### Source [Original source](https://andonlabs.com/_app/immutable/chunks/Cjn0_qj9.js) Source vendingbench Original model label Kimi K2.5 Observed 2026-10-21T16:36:40.592Z Evidence SHA-256 `1a0b043147050298c405bcb743d73e425d532464202231cd18c27f836fa5f223` Source locator `/rows/53` |  |  |  |  |  |  |
| [ARC-AGI-2](https://benchize.com/benchmarks/arc-prize%3Av2_Semi_Private.md) | 11.81% | — | 145 / 243 | 0.28usd per task | [arc prize · v2](https://arcprize.org/media/data/leaderboard/v2.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.1181 \| score_fraction \| v2_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.28 \| usd_per_task \| v2_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v2_Semi_Private harness Not reported modelGroup Not reported modelType CoT sourceModelVersion kimi-k2.5 ### Source [Original source](https://arcprize.org/media/data/leaderboard/v2.json) Source arc prize Original model label Kimi K2.5 Source version v2 Observed 2026-10-22T05:20:04.306Z Evidence SHA-256 `4351eb696e78113b0459e9bb5f0258318b905efef34f473dcea51ce641b0d94d` Source locator `/evaluations/126` |  |  |  |  |  |  |
| [ARC-AGI-1](https://benchize.com/benchmarks/arc-prize%3Av1_Semi_Private.md) | 65.33% | — | 141 / 245 | 0.15usd per task | [arc prize · v1](https://arcprize.org/media/data/leaderboard/v1.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.6533 \| score_fraction \| v1_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.15 \| usd_per_task \| v1_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v1_Semi_Private harness Not reported modelGroup Not reported modelType CoT sourceModelVersion kimi-k2.5 ### Source [Original source](https://arcprize.org/media/data/leaderboard/v1.json) Source arc prize Original model label Kimi K2.5 Source version v1 Observed 2026-10-22T05:20:04.066Z Evidence SHA-256 `2bf68d22dafba37047d07ad833ebc0e8199c9aa2f9eeaed50c75c1b704462836` Source locator `/evaluations/125` |  |  |  |  |  |  |
| [SVGBench Arena](https://benchize.com/benchmarks/svgbench%3Aarena.md) | 1,642 | — | 18 / 191 | — | [svgbench](https://svgbench.ai/api/leaderboard?shape=2) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1642 \| rating \| reported \| Higher is better \| ### Configuration Reasoning effort unknown sourceModelId model_kimik25 ### Reported statistics coverageCount 27 draws 0 judged 76 losses 31 rank 25 ratingDeviation 28 wins 45 ### Source [Original source](https://svgbench.ai/api/leaderboard?shape=2) Source svgbench Original model label Kimi K2.5 Observed 2026-10-22T04:30:04.538Z Evidence SHA-256 `5c0a9c869593820d57d2c05f6d416e1b44a740b4835e66c66e9ad8b8edc59e2c` Source locator `/rows/23` |  |  |  |  |  |  |
| [Creative Writing v3](https://benchize.com/benchmarks/eq-bench%3Acreative-writing-v3.md) | 1,578.6elo | — | 43 / 90 | — | [eq bench · creative-writing-v3](https://eqbench.com/creative_writing.js) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_score` \| 1578.6 \| elo \| overall \| Higher is better \| \| `creative_writing_score` \| 15.94 \| rubric_score \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol creative-writing-v3 sourceModelVersion moonshotai/Kimi-K2.5 ### Source [Original source](https://eqbench.com/creative_writing.js) Source eq bench Original model label moonshotai/Kimi-K2.5 Source version creative-writing-v3 Observed 2026-10-22T05:10:05.433Z Evidence SHA-256 `722ddb132e8d3a5e5c39b8d445f8475f3f7e24893a007260c6f3e3cce5c1ee18` Source locator `/leaderboardDataCreativeWritingV3/52` |  |  |  |  |  |  |
| [EQ-Bench 3](https://benchize.com/benchmarks/eq-bench%3Aeqbench3.md) | 1,544.7elo | CI 1,516.7–1,572.8 | 13 / 50 | — | [eq bench · eqbench3](https://eqbench.com/eqbench3.js) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo_norm` \| 1544.7 \| elo \| overall \| Higher is better \| \| `rubric_0_100` \| 72.5 \| percent \| overall \| Higher is better \| ### Configuration interactiveAdjustments none protocol eqbench3 sourceModelVersion moonshotai/Kimi-K2.5 ### Reported statistics Uncertainty Confidence interval: 1,516.7–1,572.8 confidenceIntervalHigh 1572.8 confidenceIntervalLow 1516.7 ### Source [Original source](https://eqbench.com/eqbench3.js) Source eq bench Original model label moonshotai/Kimi-K2.5 Source version eqbench3 Observed 2026-10-22T05:10:04.922Z Evidence SHA-256 `3672ff093e739f07ff664a2e6013bc38a6977a146e4092b4cef80ba1780542b2` Source locator `/leaderboardDataEQBench3/19` |  |  |  |  |  |  |

---
Cite as: Kimi K2.5 — Benchize, https://benchize.com/models/kimi-k2-5 (retrieved 2026-10-22)