# Slop Score > Source: Benchize (https://benchize.com) — https://benchize.com/benchmarks/eq-bench%3Aslop-score. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/benchmarks/eq-bench%3Aslop-score. Repetitive writing patterns measured from stock words, trigrams and contrast constructions. The official composite weights normalized frequencies by 60%, 15% and 25%; lower scores indicate fewer such patterns. Canonical URL: https://benchize.com/benchmarks/eq-bench%3Aslop-score Last updated: Wed, 21 Oct 2026 18:05:10 GMT Reproduction and quotation must name Benchize, link to the canonical HTML URL, and retain individual source citations. Repetitive writing patterns measured from stock words, trigrams and contrast constructions. The official composite weights normalized frequencies by 60%, 15% and 25%; lower scores indicate fewer such patterns. Writing & creativity · Models tested: 16 · Score publishers: [eq bench](https://eqbench.com/slop-score.html) ## Model results | # | Model | Score | | | --- | --- | --- | --- | | 1 | [Kimi K2 0905](https://benchize.com/models/kimi-k2-0905.md) | 18.34% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `slop_score` \| 18.340870142250065 \| percent \| official_normalized_composite \| Lower is better \| \| `slop_list_matches_per_1k_words` \| 10.118758416584026 \| matches_per_1000_words \| writing_samples \| Lower is better \| \| `slop_trigram_matches_per_1k_words` \| 0.07764888063592215 \| matches_per_1000_words \| writing_samples \| Lower is better \| \| `not_x_but_y_per_1k_chars` \| 0.1743028156360385 \| matches_per_1000_chars \| writing_samples \| Lower is better \| ### Configuration normalization official_population_min_max_10_percent_buffer protocol slop-score ### Reported statistics samples 300 ### Source [Original source](https://eqbench.com/data/leaderboard_results.json) Source eq bench Original model label moonshotai/kimi-k2-0905 Source version slop-score Evaluated 2025-11-01T08:49:26.403511+00:00 Observed 2026-10-21T16:35:04.972Z Evidence SHA-256 `16925b79d955a1cacef4d2ac91b696e73f976a4a3ceb45122544a9cf661b04de` Source locator `/results/3` | | | | | 2 | [Claude Sonnet 4.5](https://benchize.com/models/claude-sonnet-4-5.md) | 19.49% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `slop_score` \| 19.488948709359388 \| percent \| official_normalized_composite \| Lower is better \| \| `slop_list_matches_per_1k_words` \| 9.72238118855951 \| matches_per_1000_words \| writing_samples \| Lower is better \| \| `slop_trigram_matches_per_1k_words` \| 0.22891152569531875 \| matches_per_1000_words \| writing_samples \| Lower is better \| \| `not_x_but_y_per_1k_chars` \| 0.17102987605114325 \| matches_per_1000_chars \| writing_samples \| Lower is better \| ### Configuration normalization official_population_min_max_10_percent_buffer protocol slop-score ### Reported statistics samples 150 ### Source [Original source](https://eqbench.com/data/leaderboard_results.json) Source eq bench Original model label claude-sonnet-4-5 Source version slop-score Evaluated 2025-11-01T09:06:17.484557+00:00 Observed 2026-10-21T16:35:04.972Z Evidence SHA-256 `16925b79d955a1cacef4d2ac91b696e73f976a4a3ceb45122544a9cf661b04de` Source locator `/results/2` | | | | | 3 | [Kimi K2](https://benchize.com/models/kimi-k2.md) | 23.68% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `slop_score` \| 23.68230974891229 \| percent \| official_normalized_composite \| Lower is better \| \| `slop_list_matches_per_1k_words` \| 12.946588436217393 \| matches_per_1000_words \| writing_samples \| Lower is better \| \| `slop_trigram_matches_per_1k_words` \| 0.135434169811494 \| matches_per_1000_words \| writing_samples \| Lower is better \| \| `not_x_but_y_per_1k_chars` \| 0.1961294156977824 \| matches_per_1000_chars \| writing_samples \| Lower is better \| ### Configuration normalization official_population_min_max_10_percent_buffer protocol slop-score ### Reported statistics samples 300 ### Source [Original source](https://eqbench.com/data/leaderboard_results.json) Source eq bench Original model label moonshotai/kimi-k2 Source version slop-score Evaluated 2025-11-01T08:48:31.906899+00:00 Observed 2026-10-21T16:35:04.972Z Evidence SHA-256 `16925b79d955a1cacef4d2ac91b696e73f976a4a3ceb45122544a9cf661b04de` Source locator `/results/4` | | | | | 4 | [GPT-5 Mini](https://benchize.com/models/gpt-5-mini.md) | 26.28% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `slop_score` \| 26.28410611001454 \| percent \| official_normalized_composite \| Lower is better \| \| `slop_list_matches_per_1k_words` \| 15.44274370057785 \| matches_per_1000_words \| writing_samples \| Lower is better \| \| `slop_trigram_matches_per_1k_words` \| 0.20526676325343046 \| matches_per_1000_words \| writing_samples \| Lower is better \| \| `not_x_but_y_per_1k_chars` \| 0.12931438507757906 \| matches_per_1000_chars \| writing_samples \| Lower is better \| ### Configuration normalization official_population_min_max_10_percent_buffer protocol slop-score ### Reported statistics samples 300 ### Source [Original source](https://eqbench.com/data/leaderboard_results.json) Source eq bench Original model label openai/gpt-5-mini Source version slop-score Evaluated 2025-11-01T08:47:38.318245+00:00 Observed 2026-10-21T16:35:04.972Z Evidence SHA-256 `16925b79d955a1cacef4d2ac91b696e73f976a4a3ceb45122544a9cf661b04de` Source locator `/results/6` | | | | | 5 | [O3](https://benchize.com/models/o3.md) | 31.76% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `slop_score` \| 31.76046027112576 \| percent \| official_normalized_composite \| Lower is better \| \| `slop_list_matches_per_1k_words` \| 19.894018748339594 \| matches_per_1000_words \| writing_samples \| Lower is better \| \| `slop_trigram_matches_per_1k_words` \| 0.22771262666514858 \| matches_per_1000_words \| writing_samples \| Lower is better \| \| `not_x_but_y_per_1k_chars` \| 0.08584793202880854 \| matches_per_1000_chars \| writing_samples \| Lower is better \| ### Configuration normalization official_population_min_max_10_percent_buffer protocol slop-score ### Reported statistics samples 295 ### Source [Original source](https://eqbench.com/data/leaderboard_results.json) Source eq bench Original model label openai/o3 Source version slop-score Evaluated 2025-11-01T08:47:28.541099+00:00 Observed 2026-10-21T16:35:04.972Z Evidence SHA-256 `16925b79d955a1cacef4d2ac91b696e73f976a4a3ceb45122544a9cf661b04de` Source locator `/results/9` | | | | | 6 | [GPT-5 Nano](https://benchize.com/models/gpt-5-nano.md) | 34.1% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `slop_score` \| 34.09789443279408 \| percent \| official_normalized_composite \| Lower is better \| \| `slop_list_matches_per_1k_words` \| 16.923060030086415 \| matches_per_1000_words \| writing_samples \| Lower is better \| \| `slop_trigram_matches_per_1k_words` \| 0.28768762833393724 \| matches_per_1000_words \| writing_samples \| Lower is better \| \| `not_x_but_y_per_1k_chars` \| 0.302556767349028 \| matches_per_1000_chars \| writing_samples \| Lower is better \| ### Configuration normalization official_population_min_max_10_percent_buffer protocol slop-score ### Reported statistics samples 300 ### Source [Original source](https://eqbench.com/data/leaderboard_results.json) Source eq bench Original model label openai/gpt-5-nano Source version slop-score Evaluated 2025-11-01T08:47:37.288794+00:00 Observed 2026-10-21T16:35:04.972Z Evidence SHA-256 `16925b79d955a1cacef4d2ac91b696e73f976a4a3ceb45122544a9cf661b04de` Source locator `/results/7` | | | | | 7 | [Llama 4 Maverick](https://benchize.com/models/llama-4-maverick.md) | 49.18% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `slop_score` \| 49.17981324278487 \| percent \| official_normalized_composite \| Lower is better \| \| `slop_list_matches_per_1k_words` \| 23.733409337760076 \| matches_per_1000_words \| writing_samples \| Lower is better \| \| `slop_trigram_matches_per_1k_words` \| 1.1246600984462742 \| matches_per_1000_words \| writing_samples \| Lower is better \| \| `not_x_but_y_per_1k_chars` \| 0.1300421672616044 \| matches_per_1000_chars \| writing_samples \| Lower is better \| ### Configuration normalization official_population_min_max_10_percent_buffer protocol slop-score ### Reported statistics samples 300 ### Source [Original source](https://eqbench.com/data/leaderboard_results.json) Source eq bench Original model label meta-llama/llama-4-maverick Source version slop-score Evaluated 2025-11-01T08:47:06.231402+00:00 Observed 2026-10-21T16:35:04.972Z Evidence SHA-256 `16925b79d955a1cacef4d2ac91b696e73f976a4a3ceb45122544a9cf661b04de` Source locator `/results/13` | | | | | 8 | [Mistral Small 3.2 24B](https://benchize.com/models/mistral-small-3-2-24b-instruct.md) | 52.69% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `slop_score` \| 52.687891411934004 \| percent \| official_normalized_composite \| Lower is better \| \| `slop_list_matches_per_1k_words` \| 26.047923842354127 \| matches_per_1000_words \| writing_samples \| Lower is better \| \| `slop_trigram_matches_per_1k_words` \| 1.0929398369436494 \| matches_per_1000_words \| writing_samples \| Lower is better \| \| `not_x_but_y_per_1k_chars` \| 0.15083710168057302 \| matches_per_1000_chars \| writing_samples \| Lower is better \| ### Configuration normalization official_population_min_max_10_percent_buffer protocol slop-score ### Reported statistics samples 300 ### Source [Original source](https://eqbench.com/data/leaderboard_results.json) Source eq bench Original model label mistralai/Mistral-Small-3.2-24B-Instruct-2506 Source version slop-score Evaluated 2025-11-01T08:47:38.986210+00:00 Observed 2026-10-21T16:35:04.972Z Evidence SHA-256 `16925b79d955a1cacef4d2ac91b696e73f976a4a3ceb45122544a9cf661b04de` Source locator `/results/15` | | | | | 9 | [DeepSeek V3.2 Exp](https://benchize.com/models/deepseek-v3-2-exp.md) | 54.22% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `slop_score` \| 54.218303717025776 \| percent \| official_normalized_composite \| Lower is better \| \| `slop_list_matches_per_1k_words` \| 23.950797771784337 \| matches_per_1000_words \| writing_samples \| Lower is better \| \| `slop_trigram_matches_per_1k_words` \| 0.5217654324099513 \| matches_per_1000_words \| writing_samples \| Lower is better \| \| `not_x_but_y_per_1k_chars` \| 0.5690958453957651 \| matches_per_1000_chars \| writing_samples \| Lower is better \| ### Configuration normalization official_population_min_max_10_percent_buffer protocol slop-score ### Reported statistics samples 300 ### Source [Original source](https://eqbench.com/data/leaderboard_results.json) Source eq bench Original model label deepseek/deepseek-v3.2-exp Source version slop-score Evaluated 2025-11-01T08:49:04.775646+00:00 Observed 2026-10-21T16:35:04.972Z Evidence SHA-256 `16925b79d955a1cacef4d2ac91b696e73f976a4a3ceb45122544a9cf661b04de` Source locator `/results/14` | | | | | 10 | [Mistral Nemo](https://benchize.com/models/mistral-nemo.md) | 54.37% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `slop_score` \| 54.371114036596545 \| percent \| official_normalized_composite \| Lower is better \| \| `slop_list_matches_per_1k_words` \| 26.406771123508896 \| matches_per_1000_words \| writing_samples \| Lower is better \| \| `slop_trigram_matches_per_1k_words` \| 1.0112419577644303 \| matches_per_1000_words \| writing_samples \| Lower is better \| \| `not_x_but_y_per_1k_chars` \| 0.22976260708034502 \| matches_per_1000_chars \| writing_samples \| Lower is better \| ### Configuration normalization official_population_min_max_10_percent_buffer protocol slop-score ### Reported statistics samples 299 ### Source [Original source](https://eqbench.com/data/leaderboard_results.json) Source eq bench Original model label mistralai/mistral-nemo Source version slop-score Evaluated 2025-11-01T08:47:16.734702+00:00 Observed 2026-10-21T16:35:04.972Z Evidence SHA-256 `16925b79d955a1cacef4d2ac91b696e73f976a4a3ceb45122544a9cf661b04de` Source locator `/results/16` | | | | | 11 | [GLM-4.5](https://benchize.com/models/glm-4-5.md) | 59.93% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `slop_score` \| 59.93007991040196 \| percent \| official_normalized_composite \| Lower is better \| \| `slop_list_matches_per_1k_words` \| 28.446055294314608 \| matches_per_1000_words \| writing_samples \| Lower is better \| \| `slop_trigram_matches_per_1k_words` \| 0.7900866158152431 \| matches_per_1000_words \| writing_samples \| Lower is better \| \| `not_x_but_y_per_1k_chars` \| 0.42388987350114976 \| matches_per_1000_chars \| writing_samples \| Lower is better \| ### Configuration normalization official_population_min_max_10_percent_buffer protocol slop-score ### Reported statistics samples 299 ### Source [Original source](https://eqbench.com/data/leaderboard_results.json) Source eq bench Original model label z-ai/glm-4.5 Source version slop-score Evaluated 2025-11-01T08:48:31.386328+00:00 Observed 2026-10-21T16:35:04.972Z Evidence SHA-256 `16925b79d955a1cacef4d2ac91b696e73f976a4a3ceb45122544a9cf661b04de` Source locator `/results/17` | | | | | 12 | [DeepSeek R1](https://benchize.com/models/deepseek-r1.md) | 67.87% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `slop_score` \| 67.87064135308208 \| percent \| official_normalized_composite \| Lower is better \| \| `slop_list_matches_per_1k_words` \| 40.16025438049749 \| matches_per_1000_words \| writing_samples \| Lower is better \| \| `slop_trigram_matches_per_1k_words` \| 0.6999463374474624 \| matches_per_1000_words \| writing_samples \| Lower is better \| \| `not_x_but_y_per_1k_chars` \| 0.13681829789146704 \| matches_per_1000_chars \| writing_samples \| Lower is better \| ### Configuration normalization official_population_min_max_10_percent_buffer protocol slop-score ### Reported statistics samples 299 ### Source [Original source](https://eqbench.com/data/leaderboard_results.json) Source eq bench Original model label deepseek/deepseek-r1 Source version slop-score Evaluated 2025-11-01T08:48:19.788475+00:00 Observed 2026-10-21T16:35:04.972Z Evidence SHA-256 `16925b79d955a1cacef4d2ac91b696e73f976a4a3ceb45122544a9cf661b04de` Source locator `/results/21` | | | | | 13 | [Gemma 3 27B](https://benchize.com/models/gemma-3-27b-it.md) | 69.48% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `slop_score` \| 69.48152692002944 \| percent \| official_normalized_composite \| Lower is better \| \| `slop_list_matches_per_1k_words` \| 32.26903897173587 \| matches_per_1000_words \| writing_samples \| Lower is better \| \| `slop_trigram_matches_per_1k_words` \| 0.7818818284097658 \| matches_per_1000_words \| writing_samples \| Lower is better \| \| `not_x_but_y_per_1k_chars` \| 0.577146282667755 \| matches_per_1000_chars \| writing_samples \| Lower is better \| ### Configuration normalization official_population_min_max_10_percent_buffer protocol slop-score ### Reported statistics samples 300 ### Source [Original source](https://eqbench.com/data/leaderboard_results.json) Source eq bench Original model label google/gemma-3-27b-it Source version slop-score Evaluated 2025-11-01T08:21:30.159894+00:00 Observed 2026-10-21T16:35:04.972Z Evidence SHA-256 `16925b79d955a1cacef4d2ac91b696e73f976a4a3ceb45122544a9cf661b04de` Source locator `/results/18` | | | | | 14 | [Gemma 3 12B](https://benchize.com/models/gemma-3-12b-it.md) | 70.61% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `slop_score` \| 70.60667139108082 \| percent \| official_normalized_composite \| Lower is better \| \| `slop_list_matches_per_1k_words` \| 36.3532116414076 \| matches_per_1000_words \| writing_samples \| Lower is better \| \| `slop_trigram_matches_per_1k_words` \| 0.9978664402630838 \| matches_per_1000_words \| writing_samples \| Lower is better \| \| `not_x_but_y_per_1k_chars` \| 0.3077912133055163 \| matches_per_1000_chars \| writing_samples \| Lower is better \| ### Configuration normalization official_population_min_max_10_percent_buffer protocol slop-score ### Reported statistics samples 300 ### Source [Original source](https://eqbench.com/data/leaderboard_results.json) Source eq bench Original model label google/gemma-3-12b-it Source version slop-score Evaluated 2025-11-01T08:47:35.019642+00:00 Observed 2026-10-21T16:35:04.972Z Evidence SHA-256 `16925b79d955a1cacef4d2ac91b696e73f976a4a3ceb45122544a9cf661b04de` Source locator `/results/19` | | | | | 15 | [Gemini 2.5 Flash](https://benchize.com/models/gemini-2-5-flash.md) | 77.65% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `slop_score` \| 77.64730489855025 \| percent \| official_normalized_composite \| Lower is better \| \| `slop_list_matches_per_1k_words` \| 40.15792442188381 \| matches_per_1000_words \| writing_samples \| Lower is better \| \| `slop_trigram_matches_per_1k_words` \| 0.9512050121187177 \| matches_per_1000_words \| writing_samples \| Lower is better \| \| `not_x_but_y_per_1k_chars` \| 0.3864697004930431 \| matches_per_1000_chars \| writing_samples \| Lower is better \| ### Configuration normalization official_population_min_max_10_percent_buffer protocol slop-score ### Reported statistics samples 300 ### Source [Original source](https://eqbench.com/data/leaderboard_results.json) Source eq bench Original model label google/gemini-2.5-flash Source version slop-score Evaluated 2025-11-01T08:46:59.605345+00:00 Observed 2026-10-21T16:35:04.972Z Evidence SHA-256 `16925b79d955a1cacef4d2ac91b696e73f976a4a3ceb45122544a9cf661b04de` Source locator `/results/20` | | | | | 16 | [Gemma 3 4B](https://benchize.com/models/gemma-3-4b-it.md) | 85.23% | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `slop_score` \| 85.23387975443494 \| percent \| official_normalized_composite \| Lower is better \| \| `slop_list_matches_per_1k_words` \| 40.44117647058824 \| matches_per_1000_words \| writing_samples \| Lower is better \| \| `slop_trigram_matches_per_1k_words` \| 0.585844093735055 \| matches_per_1000_words \| writing_samples \| Lower is better \| \| `not_x_but_y_per_1k_chars` \| 0.8114468877690987 \| matches_per_1000_chars \| writing_samples \| Lower is better \| ### Configuration normalization official_population_min_max_10_percent_buffer protocol slop-score ### Reported statistics samples 150 ### Source [Original source](https://eqbench.com/data/leaderboard_results.json) Source eq bench Original model label google/gemma-3-4b-it Source version slop-score Evaluated 2025-10-25T09:50:18.940801+00:00 Observed 2026-10-21T16:35:04.972Z Evidence SHA-256 `16925b79d955a1cacef4d2ac91b696e73f976a4a3ceb45122544a9cf661b04de` Source locator `/results/22` | | | | --- Cite as: Slop Score — Benchize, https://benchize.com/benchmarks/eq-bench%3Aslop-score (retrieved 2026-10-21)