# GLM-5.2Max > Source: Benchize (https://benchize.com) — https://benchize.com/models/glm-5-2-max. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/glm-5-2-max. Z.ai Canonical URL: https://benchize.com/models/glm-5-2-max Last updated: Thu, 22 Oct 2026 07:10:12 GMT Reproduction and quotation must name Benchize, link to the canonical HTML URL, and retain individual source citations. Z.ai ## Benchmarks | Benchmark | Score | ± | Rank | Cost | Latency | Source | | | --- | --- | --- | --- | --- | --- | --- | --- | | [Arena text / industry entertainment and sports and media](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_entertainment_and_sports_and_media.md) | 1,449.92 | — | 24 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1449.9205563214914 \| rating \| reported \| Higher is better \| ### Configuration category industry_entertainment_and_sports_and_media config text Reasoning effort max thinkingEnabled true ### Reported statistics lower 1443.530971032195 rank 25 upper 1456.3101416107877 variance 10.627941642705018 votes 12713 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GLM-5.2 (Max) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/4717/row` | | | | | | | | | [Arena text style control / chinese](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Achinese.md) | 1,522.56 | — | 27 / 168 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1522.559906355456 \| rating \| reported \| Higher is better \| ### Configuration category chinese config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1512.2391838838614 rank 28 upper 1532.8806288270505 variance 27.72834938692114 votes 3696 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GLM-5.2 (Max) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/444/row` | | | | | | | | | [Arena text / creative writing](https://benchize.com/benchmarks/lmarena%3Atext%3Acreative_writing.md) | 1,462.73 | — | 22 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1462.7290646110946 \| rating \| reported \| Higher is better \| ### Configuration category creative_writing config text Reasoning effort max thinkingEnabled true ### Reported statistics lower 1455.8065620902282 rank 23 upper 1469.6515671319612 variance 12.4746986465792 votes 10217 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GLM-5.2 (Max) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/1244/row` | | | | | | | | | [Arena text style control / industry writing and literature and language](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_writing_and_literature_and_language.md) | 1,460.5 | — | 33 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1460.4998760497454 \| rating \| reported \| Higher is better \| ### Configuration category industry_writing_and_literature_and_language config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1454.3497007396888 rank 36 upper 1466.6500513598016 variance 9.846430252138425 votes 13740 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GLM-5.2 (Max) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/7153/row` | | | | | | | | | [Arena text / math](https://benchize.com/benchmarks/lmarena%3Atext%3Amath.md) | 1,482.89 | — | 30 / 170 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1482.8882703533304 \| rating \| reported \| Higher is better \| ### Configuration category math config text Reasoning effort max thinkingEnabled true ### Reported statistics lower 1470.4355553388875 rank 31 upper 1495.3409853677736 variance 40.36750580158819 votes 2303 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GLM-5.2 (Max) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/8943/row` | | | | | | | | | [Arena text / industry medicine and healthcare](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_medicine_and_healthcare.md) | 1,474.71 | — | 27 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1474.7124490790975 \| rating \| reported \| Higher is better \| ### Configuration category industry_medicine_and_healthcare config text Reasoning effort max thinkingEnabled true ### Reported statistics lower 1464.4474089211399 rank 31 upper 1484.9774892370551 variance 27.4299567853861 votes 3768 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GLM-5.2 (Max) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/6343/row` | | | | | | | | | [Arena text style control / math](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Amath.md) | 1,486.58 | — | 34 / 170 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1486.583018419692 \| rating \| reported \| Higher is better \| ### Configuration category math config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1474.1532466979972 rank 34 upper 1499.0127901413866 variance 40.218893984011096 votes 2303 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GLM-5.2 (Max) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/8946/row` | | | | | | | | | [GDPval-AA v2 (Elo-score)](https://benchize.com/benchmarks/gdpval-aa-v2.md) | 1,514elo | — | 5 / 6 | — | — | [Moonshot AI · sha256:0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c](https://www.kimi.ai/blog/kimi-k3) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1514 \| elo \| reported \| Higher is better \| ### Configuration Reasoning effort max thinkingEnabled true ### Source Score publisher [Moonshot AI](https://www.kimi.ai/blog/kimi-k3) Collected via [moonshot k3](https://www.kimi.ai/blog/kimi-k3) Publisher reference Referenced by the collection source; the upstream result has not been independently captured. Benchmark [https://www.kimi.ai/blog/kimi-k3](https://www.kimi.ai/blog/kimi-k3) [Collected via](https://www.kimi.ai/blog/kimi-k3) Source Moonshot AI Original model label GLM-5.2 (max) Source version sha256:0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c Observed 2026-10-21T16:31:44.130Z Evidence SHA-256 `0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c` Source locator `/flight/sheet/data/8/scores/5` | | | | | | | | | [Toolathlon-Verified](https://benchize.com/benchmarks/toolathlon-verified.md) | 59.9% | — | 6 / 6 | — | — | [Moonshot AI · sha256:0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c](https://www.kimi.ai/blog/kimi-k3) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 59.9 \| percent \| reported \| Higher is better \| ### Configuration Reasoning effort max thinkingEnabled true ### Source Score publisher [Moonshot AI](https://www.kimi.ai/blog/kimi-k3) Collected via [moonshot k3](https://www.kimi.ai/blog/kimi-k3) Publisher reference Referenced by the collection source; the upstream result has not been independently captured. Benchmark [https://www.kimi.ai/blog/kimi-k3](https://www.kimi.ai/blog/kimi-k3) [Collected via](https://www.kimi.ai/blog/kimi-k3) Source Moonshot AI Original model label GLM-5.2 (max) Source version sha256:0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c Observed 2026-10-21T16:31:44.130Z Evidence SHA-256 `0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c` Source locator `/flight/sheet/data/11/scores/5` | | | | | | | | | [Short Story Writing — Pairwise Comparison](https://benchize.com/benchmarks/lechmazur-short-story%3Apairwise.md) | 0.46 | 95% CI 0.35–0.55 | 24 / 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` \| 0.4574569700670838 \| index \| pooled_observed_panel \| Higher is better \| \| `win_probability` \| 0.5686581363155423 \| score_fraction \| comparison_pool \| Higher is better \| ### Configuration benchmarkScope data/writing_gemini_argon_20261013 Reasoning effort max thinkingEnabled true ### Reported statistics Uncertainty 95% confidence interval: 0.35–0.55 bootstrapSamples 300 confidenceInterval95 ["0.3452674156005926","0.5479126902897905"] sourceRank 24 ### 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 GLM-5.2 (max) Source version 8ba548d1cffefa5c472d3832e05f64e119a88fa4 Observed 2026-10-22T07:10:06.634Z Evidence SHA-256 `c36baebed9f302ff7ad8fe97907d72e1757a015a39b6a3b23437597cf8e3bff6` Source locator `/rows/23` | | | | | | | | | [Arena text / spanish](https://benchize.com/benchmarks/lmarena%3Atext%3Aspanish.md) | 1,477.97 | — | 17 / 155 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1477.973293993492 \| rating \| reported \| Higher is better \| ### Configuration category spanish config text Reasoning effort max thinkingEnabled true ### Reported statistics lower 1462.145053484549 rank 17 upper 1493.801534502435 variance 65.21824372014794 votes 1548 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GLM-5.2 (Max) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/10781/row` | | | | | | | | | [Arena text / german](https://benchize.com/benchmarks/lmarena%3Atext%3Agerman.md) | 1,470.12 | — | 26 / 149 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1470.1209677021734 \| rating \| reported \| Higher is better \| ### Configuration category german config text Reasoning effort max thinkingEnabled true ### Reported statistics lower 1449.890029518922 rank 31 upper 1490.351905885425 variance 106.5456845638099 votes 913 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GLM-5.2 (Max) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/3167/row` | | | | | | | | | [Arena text style control / russian](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Arussian.md) | 1,473.59 | — | 35 / 172 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1473.5872565355398 \| rating \| reported \| Higher is better \| ### Configuration category russian config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1465.4169507431347 rank 42 upper 1481.757562327945 variance 17.377225647143252 votes 6017 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GLM-5.2 (Max) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10425/row` | | | | | | | | | [Kimi Code Bench 2.0 (Internal)](https://benchize.com/benchmarks/kimi-code-bench-2.md) | 64.2% | — | 6 / 6 | — | — | [Moonshot AI · sha256:0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c](https://www.kimi.ai/blog/kimi-k3) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 64.2 \| percent \| reported \| Higher is better \| ### Configuration benchmarkVisibility internal harness Claude Code Reasoning effort max thinkingEnabled true ### Source Score publisher [Moonshot AI](https://www.kimi.ai/blog/kimi-k3) Collected via [moonshot k3](https://www.kimi.ai/blog/kimi-k3) Publisher reference Referenced by the collection source; the upstream result has not been independently captured. Benchmark [https://www.kimi.ai/blog/kimi-k3](https://www.kimi.ai/blog/kimi-k3) [Collected via](https://www.kimi.ai/blog/kimi-k3) Source Moonshot AI Original model label GLM-5.2 (max) Source version sha256:0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c Observed 2026-10-21T16:31:44.130Z Evidence SHA-256 `0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c` Source locator `/flight/sheet/data/7/scores/5` | | | | | | | | | [MCP Atlas](https://benchize.com/benchmarks/scale%3Amcp_atlas.md) | 82.6% | — | 6 / 6 | — | — | [Moonshot AI · sha256:0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c](https://www.kimi.ai/blog/kimi-k3) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 82.6 \| percent \| reported \| Higher is better \| ### Configuration judgeModel Gemini 3.1 Pro maxTurns 100 Reasoning effort max subset public taskCount 500 thinkingEnabled true ### Source Score publisher [Moonshot AI](https://www.kimi.ai/blog/kimi-k3) Collected via [moonshot k3](https://www.kimi.ai/blog/kimi-k3) Publisher reference Referenced by the collection source; the upstream result has not been independently captured. Benchmark [https://www.kimi.ai/blog/kimi-k3](https://www.kimi.ai/blog/kimi-k3) [Collected via](https://www.kimi.ai/blog/kimi-k3) Source Moonshot AI Original model label GLM-5.2 (max) Source version sha256:0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c Observed 2026-10-21T16:31:44.130Z Evidence SHA-256 `0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c` Source locator `/flight/sheet/data/12/scores/5` | | | | | | | | | [Arena text / japanese](https://benchize.com/benchmarks/lmarena%3Atext%3Ajapanese.md) | 1,450.02 | — | 29 / 138 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1450.0170771583114 \| rating \| reported \| Higher is better \| ### Configuration category japanese config text Reasoning effort max thinkingEnabled true ### Reported statistics lower 1427.6204937401478 rank 31 upper 1472.413660576475 variance 130.57720314599746 votes 835 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GLM-5.2 (Max) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/7981/row` | | | | | | | | | [Arena text / english](https://benchize.com/benchmarks/lmarena%3Atext%3Aenglish.md) | 1,474.94 | — | 30 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1474.9366050989324 \| rating \| reported \| Higher is better \| ### Configuration category english config text Reasoning effort max thinkingEnabled true ### Reported statistics lower 1469.707090264817 rank 33 upper 1480.1661199330476 variance 7.1191249670329855 votes 20996 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GLM-5.2 (Max) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/1669/row` | | | | | | | | | [Arena text / french](https://benchize.com/benchmarks/lmarena%3Atext%3Afrench.md) | 1,478.55 | — | 31 / 152 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1478.5513256107752 \| rating \| reported \| Higher is better \| ### Configuration category french config text Reasoning effort max thinkingEnabled true ### Reported statistics lower 1463.4710505311955 rank 35 upper 1493.6316006903548 variance 59.200087021809516 votes 1902 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GLM-5.2 (Max) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/2872/row` | | | | | | | | | [Arena text style control / german](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Agerman.md) | 1,476.79 | — | 29 / 149 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1476.7938085427284 \| rating \| reported \| Higher is better \| ### Configuration category german config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1456.443080972779 rank 35 upper 1497.1445361126775 variance 107.81115507349371 votes 913 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GLM-5.2 (Max) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/3171/row` | | | | | | | | | [Arena text style control / non english](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Anon_english.md) | 1,462.62 | — | 34 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1462.619021343197 \| rating \| reported \| Higher is better \| ### Configuration category non_english config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1457.8593078505378 rank 39 upper 1467.378734835856 variance 5.897465934076453 votes 30215 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GLM-5.2 (Max) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/9769/row` | | | | | | | | | [Arena text style control / industry entertainment and sports and media](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_entertainment_and_sports_and_media.md) | 1,447.32 | — | 36 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1447.3156268144464 \| rating \| reported \| Higher is better \| ### Configuration category industry_entertainment_and_sports_and_media config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1440.877495836537 rank 41 upper 1453.753757792356 variance 10.790049411808651 votes 12713 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GLM-5.2 (Max) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/4733/row` | | | | | | | | | [Arena text style control / coding](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Acoding.md) | 1,514.56 | — | 40 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1514.5615409644945 \| rating \| reported \| Higher is better \| ### Configuration category coding config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1508.4106174894196 rank 45 upper 1520.7124644395694 variance 9.848826022138923 votes 13716 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GLM-5.2 (Max) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/854/row` | | | | | | | | | [Arena text / industry writing and literature and language](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_writing_and_literature_and_language.md) | 1,463.14 | — | 27 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1463.1425515127735 \| rating \| reported \| Higher is better \| ### Configuration category industry_writing_and_literature_and_language config text Reasoning effort max thinkingEnabled true ### Reported statistics lower 1457.0155541427266 rank 28 upper 1469.2695488828206 variance 9.772354338495516 votes 13740 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GLM-5.2 (Max) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/7145/row` | | | | | | | | | [Arena text style control / longer query](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Alonger_query.md) | 1,486.94 | — | 28 / 172 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1486.943057046514 \| rating \| reported \| Higher is better \| ### Configuration category longer_query config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1481.604508138415 rank 31 upper 1492.281605954613 variance 7.419083680042232 votes 23394 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GLM-5.2 (Max) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/8548/row` | | | | | | | | | [Arena text / industry legal and government](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_legal_and_government.md) | 1,486.03 | — | 23 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1486.0317862726051 \| rating \| reported \| Higher is better \| ### Configuration category industry_legal_and_government config text Reasoning effort max thinkingEnabled true ### Reported statistics lower 1476.2673506498707 rank 23 upper 1495.7962218953396 variance 24.819790470459463 votes 4161 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GLM-5.2 (Max) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/5130/row` | | | | | | | | | [Arena text style control / industry business and management and financial operations](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_business_and_management_and_financial_operations.md) | 1,465.99 | — | 41 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1465.992762521461 \| rating \| reported \| Higher is better \| ### Configuration category industry_business_and_management_and_financial_operations config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1459.216945900787 rank 48 upper 1472.7685791421347 variance 11.951629060728484 votes 9744 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GLM-5.2 (Max) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/4330/row` | | | | | | | | | [GPQA Diamond](https://benchize.com/benchmarks/gpqa-diamond.md) | 91.2% | — | 5 / 6 | — | — | [Moonshot AI · sha256:0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c](https://www.kimi.ai/blog/kimi-k3) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 91.2 \| percent \| reported \| Higher is better \| ### Configuration Reasoning effort max thinkingEnabled true ### Source Score publisher [Moonshot AI](https://www.kimi.ai/blog/kimi-k3) Collected via [moonshot k3](https://www.kimi.ai/blog/kimi-k3) Publisher reference Referenced by the collection source; the upstream result has not been independently captured. Benchmark [https://www.kimi.ai/blog/kimi-k3](https://www.kimi.ai/blog/kimi-k3) [Collected via](https://www.kimi.ai/blog/kimi-k3) Source Moonshot AI Original model label GLM-5.2 (max) Source version sha256:0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c Observed 2026-10-21T16:31:44.130Z Evidence SHA-256 `0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c` Source locator `/flight/sheet/data/20/scores/5` | | | | | | | | | [AA-Briefcase (Elo-score)](https://benchize.com/benchmarks/aa-briefcase.md) | 1,260elo | — | 5 / 6 | — | — | [Moonshot AI · sha256:0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c](https://www.kimi.ai/blog/kimi-k3) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1260 \| elo \| reported \| Higher is better \| ### Configuration Reasoning effort max thinkingEnabled true ### Source Score publisher [Moonshot AI](https://www.kimi.ai/blog/kimi-k3) Collected via [moonshot k3](https://www.kimi.ai/blog/kimi-k3) Publisher reference Referenced by the collection source; the upstream result has not been independently captured. Benchmark [https://www.kimi.ai/blog/kimi-k3](https://www.kimi.ai/blog/kimi-k3) [Collected via](https://www.kimi.ai/blog/kimi-k3) Source Moonshot AI Original model label GLM-5.2 (max) Source version sha256:0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c Observed 2026-10-21T16:31:44.130Z Evidence SHA-256 `0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c` Source locator `/flight/sheet/data/15/scores/5` | | | | | | | | | [Arena text / exclude ties](https://benchize.com/benchmarks/lmarena%3Atext%3Aexclude_ties.md) | 1,475.81 | — | 29 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1475.8062532547826 \| rating \| reported \| Higher is better \| ### Configuration category exclude_ties config text Reasoning effort max thinkingEnabled true ### Reported statistics lower 1470.5085668547251 rank 32 upper 1481.1039396548401 variance 7.3059435238936725 votes 37919 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GLM-5.2 (Max) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/2085/row` | | | | | | | | | [Arena text style control / polish](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Apolish.md) | 1,458.67 | — | 43 / 137 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1458.6654175163087 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1437.7299801871623 rank 59 upper 1479.6008548454552 variance 114.095336334601 votes 834 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GLM-5.2 (Max) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10206/row` | | | | | | | | | [Arena text style control / industry legal and government](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_legal_and_government.md) | 1,491.2 | — | 25 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1491.197661168546 \| rating \| reported \| Higher is better \| ### Configuration category industry_legal_and_government config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1481.3602000338353 rank 26 upper 1501.0351223032567 variance 25.192419363083655 votes 4161 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GLM-5.2 (Max) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/5133/row` | | | | | | | | | [MLS Bench](https://benchize.com/benchmarks/mls-bench-lite.md) | 40.4% | — | 5 / 6 | — | — | [Moonshot AI · sha256:0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c](https://www.kimi.ai/blog/kimi-k3) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 40.4 \| percent \| reported \| Higher is better \| ### Configuration harness Claude Code Reasoning effort max thinkingEnabled true ### Source Score publisher [Moonshot AI](https://www.kimi.ai/blog/kimi-k3) Collected via [moonshot k3](https://www.kimi.ai/blog/kimi-k3) Publisher reference Referenced by the collection source; the upstream result has not been independently captured. Benchmark [https://www.kimi.ai/blog/kimi-k3](https://www.kimi.ai/blog/kimi-k3) [Collected via](https://www.kimi.ai/blog/kimi-k3) Source Moonshot AI Original model label GLM-5.2 (max) Source version sha256:0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c Observed 2026-10-21T16:31:44.130Z Evidence SHA-256 `0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c` Source locator `/flight/sheet/data/6/scores/5` | | | | | | | | | [Arena text / longer query](https://benchize.com/benchmarks/lmarena%3Atext%3Alonger_query.md) | 1,480.07 | — | 28 / 172 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1480.0699249524732 \| rating \| reported \| Higher is better \| ### Configuration category longer_query config text Reasoning effort max thinkingEnabled true ### Reported statistics lower 1474.765170699558 rank 29 upper 1485.3746792053885 variance 7.325450824105966 votes 23394 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GLM-5.2 (Max) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/8546/row` | | | | | | | | | [AutomationBench](https://benchize.com/benchmarks/zapier%3Aautomationbench.md) | 12.9% | — | 6 / 6 | — | — | [Moonshot AI · sha256:0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c](https://www.kimi.ai/blog/kimi-k3) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 12.9 \| percent \| reported \| Higher is better \| ### Configuration Reasoning effort max subset public taskCount 600 thinkingEnabled true ### Source Score publisher [Moonshot AI](https://www.kimi.ai/blog/kimi-k3) Collected via [moonshot k3](https://www.kimi.ai/blog/kimi-k3) Publisher reference Referenced by the collection source; the upstream result has not been independently captured. Benchmark [https://www.kimi.ai/blog/kimi-k3](https://www.kimi.ai/blog/kimi-k3) [Collected via](https://www.kimi.ai/blog/kimi-k3) Source Moonshot AI Original model label GLM-5.2 (max) Source version sha256:0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c Observed 2026-10-21T16:31:44.130Z Evidence SHA-256 `0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c` Source locator `/flight/sheet/data/13/scores/5` | | | | | | | | | [Arena text style control / industry software and it services](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_software_and_it_services.md) | 1,506.31 | — | 37 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1506.3126137440445 \| rating \| reported \| Higher is better \| ### Configuration category industry_software_and_it_services config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1500.9061369408744 rank 43 upper 1511.7190905472146 variance 7.609086231967933 votes 19889 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GLM-5.2 (Max) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/6743/row` | | | | | | | | | [SWE Marathon](https://benchize.com/benchmarks/swe-marathon.md) | 13% | — | 6 / 6 | — | — | [Moonshot AI · sha256:0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c](https://www.kimi.ai/blog/kimi-k3) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 13.0 \| percent \| reported \| Higher is better \| ### Configuration Reasoning effort max thinkingEnabled true ### Source Score publisher [Moonshot AI](https://www.kimi.ai/blog/kimi-k3) Collected via [moonshot k3](https://www.kimi.ai/blog/kimi-k3) Publisher reference Referenced by the collection source; the upstream result has not been independently captured. Benchmark [https://www.kimi.ai/blog/kimi-k3](https://www.kimi.ai/blog/kimi-k3) [Collected via](https://www.kimi.ai/blog/kimi-k3) Source Moonshot AI Original model label GLM-5.2 (max) Source version sha256:0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c Observed 2026-10-21T16:31:44.130Z Evidence SHA-256 `0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c` Source locator `/flight/sheet/data/4/scores/5` | | | | | | | | | [Arena text / chinese](https://benchize.com/benchmarks/lmarena%3Atext%3Achinese.md) | 1,521.9 | — | 29 / 168 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1521.903906685341 \| rating \| reported \| Higher is better \| ### Configuration category chinese config text Reasoning effort max thinkingEnabled true ### Reported statistics lower 1511.629218998034 rank 31 upper 1532.1785943726481 variance 27.481540737334413 votes 3696 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GLM-5.2 (Max) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/447/row` | | | | | | | | | [Arena text style control / hard prompts english](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ahard_prompts_english.md) | 1,498.28 | — | 36 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1498.2767134477126 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts_english config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1492.1891709461984 rank 40 upper 1504.3642559492268 variance 9.64690120016601 votes 13844 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GLM-5.2 (Max) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/3907/row` | | | | | | | | | [Terminal-Bench 2.1](https://benchize.com/benchmarks/artificial-analysis%3Aterminalbench_v2_1.md) | 82.7% | — | 6 / 6 | — | — | [Moonshot AI · sha256:0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c](https://www.kimi.ai/blog/kimi-k3) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 82.7 \| percent \| reported \| Higher is better \| ### Configuration harness Claude Code Reasoning effort max thinkingEnabled true ### Source Score publisher [Moonshot AI](https://www.kimi.ai/blog/kimi-k3) Collected via [moonshot k3](https://www.kimi.ai/blog/kimi-k3) Publisher reference Referenced by the collection source; the upstream result has not been independently captured. Benchmark [https://www.kimi.ai/blog/kimi-k3](https://www.kimi.ai/blog/kimi-k3) [Collected via](https://www.kimi.ai/blog/kimi-k3) Source Moonshot AI Original model label GLM-5.2 (max) Source version sha256:0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c Observed 2026-10-21T16:31:44.130Z Evidence SHA-256 `0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c` Source locator `/flight/sheet/data/2/scores/5` | | | | | | | | | [FrontierSWE](https://benchize.com/benchmarks/frontierswe%3Adominance.md) | 67.3% | — | 4 / 6 | — | — | [Moonshot AI · sha256:0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c](https://www.kimi.ai/blog/kimi-k3) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `dominance` \| 67.3 \| percent \| dominance_2026-07-16 \| Higher is better \| ### Configuration normalization dominance normalizationDate 2026-07-16 Reasoning effort max thinkingEnabled true ### Source Score publisher [Moonshot AI](https://www.kimi.ai/blog/kimi-k3) Collected via [moonshot k3](https://www.kimi.ai/blog/kimi-k3) Publisher reference Referenced by the collection source; the upstream result has not been independently captured. Benchmark [https://www.kimi.ai/blog/kimi-k3](https://www.kimi.ai/blog/kimi-k3) [Collected via](https://www.kimi.ai/blog/kimi-k3) Source Moonshot AI Original model label GLM-5.2 (max) Source version sha256:0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c Observed 2026-10-21T16:31:44.130Z Evidence SHA-256 `0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c` Source locator `/flight/sheet/data/3/scores/5` | | | | | | | | | [Arena text / multi turn](https://benchize.com/benchmarks/lmarena%3Atext%3Amulti_turn.md) | 1,469.26 | — | 34 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1469.2634338975154 \| rating \| reported \| Higher is better \| ### Configuration category multi_turn config text Reasoning effort max thinkingEnabled true ### Reported statistics lower 1461.9433434983966 rank 38 upper 1476.583524296634 variance 13.948795484312408 votes 8108 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GLM-5.2 (Max) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/9353/row` | | | | | | | | | [Arena text / industry business and management and financial operations](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_business_and_management_and_financial_operations.md) | 1,450.73 | — | 40 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1450.7314105316577 \| rating \| reported \| Higher is better \| ### Configuration category industry_business_and_management_and_financial_operations config text Reasoning effort max thinkingEnabled true ### Reported statistics lower 1443.9925015546269 rank 43 upper 1457.4703195086884 variance 11.821783421460726 votes 9744 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GLM-5.2 (Max) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/4325/row` | | | | | | | | | [Arena text / hard prompts english](https://benchize.com/benchmarks/lmarena%3Atext%3Ahard_prompts_english.md) | 1,480.88 | — | 32 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1480.879354439105 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts_english config text Reasoning effort max thinkingEnabled true ### Reported statistics lower 1474.835353205884 rank 35 upper 1486.9233556723261 variance 9.509395417800729 votes 13844 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GLM-5.2 (Max) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/3902/row` | | | | | | | | | [Arena text / coding](https://benchize.com/benchmarks/lmarena%3Atext%3Acoding.md) | 1,487.02 | — | 37 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1487.0181499032485 \| rating \| reported \| Higher is better \| ### Configuration category coding config text Reasoning effort max thinkingEnabled true ### Reported statistics lower 1480.9256408506276 rank 42 upper 1493.1106589558697 variance 9.662648563693853 votes 13716 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GLM-5.2 (Max) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/851/row` | | | | | | | | | [APEX-Agents](https://benchize.com/benchmarks/apex-agents.md) | 35.6% | — | 6 / 6 | — | — | [Moonshot AI · sha256:0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c](https://www.kimi.ai/blog/kimi-k3) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 35.6 \| percent \| reported \| Higher is better \| ### Configuration Reasoning effort max thinkingEnabled true ### Source Score publisher [Moonshot AI](https://www.kimi.ai/blog/kimi-k3) Collected via [moonshot k3](https://www.kimi.ai/blog/kimi-k3) Publisher reference Referenced by the collection source; the upstream result has not been independently captured. Benchmark [https://www.kimi.ai/blog/kimi-k3](https://www.kimi.ai/blog/kimi-k3) [Collected via](https://www.kimi.ai/blog/kimi-k3) Source Moonshot AI Original model label GLM-5.2 (max) Source version sha256:0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c Observed 2026-10-21T16:31:44.130Z Evidence SHA-256 `0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c` Source locator `/flight/sheet/data/16/scores/5` | | | | | | | | | [Arena text / industry life and physical and social science](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_life_and_physical_and_social_science.md) | 1,488.79 | — | 23 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1488.7864274214928 \| rating \| reported \| Higher is better \| ### Configuration category industry_life_and_physical_and_social_science config text Reasoning effort max thinkingEnabled true ### Reported statistics lower 1481.7219999008953 rank 24 upper 1495.85085494209 variance 12.991454164477192 votes 8550 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GLM-5.2 (Max) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/5521/row` | | | | | | | | | [Arena webdev / webdev](https://benchize.com/benchmarks/lmarena%3Awebdev%3Awebdev.md) | 1,604.22 | — | 26 / 107 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1604.2162197370149 \| rating \| reported \| Higher is better \| ### Configuration category webdev config webdev Reasoning effort max thinkingEnabled true ### Reported statistics lower 1598.1626439288439 rank 30 upper 1610.2697955451858 variance 9.539547806125158 votes 16657 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) Source Arena Original model label GLM-5.2 (Max) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `f82507859808110820a4ab6df15561b8864137ddefc1f6fb0c552af2e58ea738` Source locator `/rows/241/row` | | | | | | | | | [Arena text style control / japanese](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ajapanese.md) | 1,454.83 | — | 33 / 138 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1454.8317019699336 \| rating \| reported \| Higher is better \| ### Configuration category japanese config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1432.1803736407114 rank 36 upper 1477.4830302991559 variance 133.56453863678624 votes 835 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GLM-5.2 (Max) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/7986/row` | | | | | | | | | [Arena text style control / exclude ties](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aexclude_ties.md) | 1,485.84 | — | 33 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1485.8423720446797 \| rating \| reported \| Higher is better \| ### Configuration category exclude_ties config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1480.4568137331064 rank 35 upper 1491.2279303562532 variance 7.550318689116198 votes 37919 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GLM-5.2 (Max) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/2088/row` | | | | | | | | | [Arena text style control / instruction following](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ainstruction_following.md) | 1,469.87 | — | 36 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1469.8719987967775 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1464.2832706256481 rank 38 upper 1475.4607269679068 variance 8.130734710083408 votes 17693 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GLM-5.2 (Max) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/7571/row` | | | | | | | | | [DeepSWE](https://benchize.com/benchmarks/deepswe%3Av1.1.md) | 43.78% | Range 42.05–45.5% | 56 / 70 | $3.92 | 2,629.21s | [deepswe](https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `pass_at_1` \| 0.43777777777777777 \| score_fraction \| scored_rollout_attempts \| Higher is better \| \| `pass_at_4` \| 0.7699115044247787 \| score_fraction \| tasks_with_one_passing_rollout \| Higher is better \| \| `cost_per_attempt` \| 3.9199075743111114 \| USD \| scored_attempt \| Lower is better \| \| `duration` \| 2629.2083211311115 \| seconds \| scored_attempt \| Lower is better \| ### Configuration harness mini-swe-agent Reasoning effort max sourceConfiguration mini_swe_agent_glm_5_2_max ### Reported statistics Uncertainty Reported interval: 42.05–45.5% interval [0.42052148157196967,0.45503407398358586] intervalMethod 95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R)) runCount 4 sampleSize 450 taskCount 113 ### Source [Original source](https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json) Source deepswe Original model label glm-5-2 Observed 2026-10-22T03:50:05.889Z Evidence SHA-256 `a7c15d66288fd249c020b9931c017b92d1a3b90e480b3ff34974b752bd030019` Source locator `/rows/55` | | | | | | | | | [PostTrain Bench](https://benchize.com/benchmarks/posttrainbench.md) | 34.3% | — | 4 / 6 | — | — | [Moonshot AI · sha256:0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c](https://www.kimi.ai/blog/kimi-k3) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 34.3 \| percent \| reported \| Higher is better \| ### Configuration Reasoning effort max thinkingEnabled true ### Source Score publisher [Moonshot AI](https://www.kimi.ai/blog/kimi-k3) Collected via [moonshot k3](https://www.kimi.ai/blog/kimi-k3) Publisher reference Referenced by the collection source; the upstream result has not been independently captured. Benchmark [https://www.kimi.ai/blog/kimi-k3](https://www.kimi.ai/blog/kimi-k3) [Collected via](https://www.kimi.ai/blog/kimi-k3) Source Moonshot AI Original model label GLM-5.2 (max) Source version sha256:0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c Observed 2026-10-21T16:31:44.130Z Evidence SHA-256 `0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c` Source locator `/flight/sheet/data/5/scores/5` | | | | | | | | | [OfficeQA Pro — Agent Harness](https://benchize.com/benchmarks/officeqa-pro%3Aagent.md) | 41.4% | — | 6 / 6 | — | — | [Moonshot AI · sha256:0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c](https://www.kimi.ai/blog/kimi-k3) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 41.4 \| percent \| reported \| Higher is better \| ### Configuration corpusFormat rendered_pdf_images harness Claude Code machineReadablePdfText false Reasoning effort max thinkingEnabled true ### Source Score publisher [Moonshot AI](https://www.kimi.ai/blog/kimi-k3) Collected via [moonshot k3](https://www.kimi.ai/blog/kimi-k3) Publisher reference Referenced by the collection source; the upstream result has not been independently captured. Benchmark [https://www.kimi.ai/blog/kimi-k3](https://www.kimi.ai/blog/kimi-k3) [Collected via](https://www.kimi.ai/blog/kimi-k3) Source Moonshot AI Original model label GLM-5.2 (max) Source version sha256:0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c Observed 2026-10-21T16:31:44.130Z Evidence SHA-256 `0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c` Source locator `/flight/sheet/data/17/scores/5` | | | | | | | | | [Arena text / korean](https://benchize.com/benchmarks/lmarena%3Atext%3Akorean.md) | 1,439.55 | — | 27 / 144 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1439.5458149160318 \| rating \| reported \| Higher is better \| ### Configuration category korean config text Reasoning effort max thinkingEnabled true ### Reported statistics lower 1419.6736464189216 rank 28 upper 1459.4179834131419 variance 102.80028999664779 votes 988 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GLM-5.2 (Max) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/8261/row` | | | | | | | | | [Arena text / overall](https://benchize.com/benchmarks/lmarena%3Atext.md) | 1,470.36 | — | 29 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1470.3641370966138 \| rating \| reported \| Higher is better \| ### Configuration category overall config text Reasoning effort max thinkingEnabled true ### Reported statistics lower 1466.2499403522163 rank 32 upper 1474.4783338410116 variance 4.406298659360352 votes 51221 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GLM-5.2 (Max) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/31/row` | | | | | | | | | [Arena text / industry mathematical](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_mathematical.md) | 1,489.1 | — | 31 / 169 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1489.1049524459968 \| rating \| reported \| Higher is better \| ### Configuration category industry_mathematical config text Reasoning effort max thinkingEnabled true ### Reported statistics lower 1477.5108473472342 rank 34 upper 1500.6990575447594 variance 34.99276689288101 votes 2786 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GLM-5.2 (Max) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/5946/row` | | | | | | | | | [AutomationBench](https://benchize.com/benchmarks/zapier%3Aautomationbench.md) | 7.76% | — | 77 / 113 | $0.22 | — | [zapier](https://framerusercontent.com/sites/4WTSl4BNjd1q9QFEFibC6h/lOvLnhItj8S8-1vyjH_s33Jn-WmUXPmiJ5Diajl0Q38.CMutaHYl.mjs) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 7.76 \| percent \| reported \| Higher is better \| \| `cost` \| 0.22 \| USD \| per_task \| Lower is better \| ### Configuration benchmarkVersion 1.0.6 costFootnote false Fallback policy Not reported Reasoning effort max Model configuration GLM 5.2 (Max) thinkingEnabled true ### Reported statistics rank 87 ### Source [Original source](https://framerusercontent.com/sites/4WTSl4BNjd1q9QFEFibC6h/lOvLnhItj8S8-1vyjH_s33Jn-WmUXPmiJ5Diajl0Q38.CMutaHYl.mjs) Source zapier Original model label GLM 5.2 (Max) Observed 2026-10-21T16:34:56.783Z Evidence SHA-256 `43978e38f018789fa59c11de5328abe9e5905bfa9a5a4d601fa3aa4d9c153b0d` Source locator `/rows/86` | | | | | | | | | [Arena text style control / french](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Afrench.md) | 1,491.14 | — | 32 / 152 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1491.139724026139 \| rating \| reported \| Higher is better \| ### Configuration category french config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1476.0126074292693 rank 39 upper 1506.266840623009 variance 59.56842627144202 votes 1902 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GLM-5.2 (Max) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/2876/row` | | | | | | | | | [Arena webdev / webdev-html](https://benchize.com/benchmarks/lmarena%3Awebdev%3Awebdev-html.md) | 1,565.48 | — | 33 / 106 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1565.4786078366437 \| rating \| reported \| Higher is better \| ### Configuration category webdev-html config webdev Reasoning effort max thinkingEnabled true ### Reported statistics lower 1550.9208620545949 rank 37 upper 1580.0363536186924 variance 55.168614879610914 votes 2032 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) Source Arena Original model label GLM-5.2 (Max) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `f82507859808110820a4ab6df15561b8864137ddefc1f6fb0c552af2e58ea738` Source locator `/rows/396/row` | | | | | | | | | [Arena text style control / expert](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aexpert.md) | 1,501.55 | — | 37 / 170 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1501.5486721121722 \| rating \| reported \| Higher is better \| ### Configuration category expert config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1492.9065809293556 rank 40 upper 1510.190763294989 variance 19.442025412268617 votes 5377 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GLM-5.2 (Max) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/2510/row` | | | | | | | | | [SpreadsheetBench v2-full](https://benchize.com/benchmarks/spreadsheetbench%3Av2-full.md) | 28.12% | — | 6 / 6 | — | — | [Moonshot AI · sha256:0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c](https://www.kimi.ai/blog/kimi-k3) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 28.12 \| percent \| reported \| Higher is better \| ### Configuration harness Claude Code Reasoning effort max thinkingEnabled true ### Source Score publisher [Moonshot AI](https://www.kimi.ai/blog/kimi-k3) Collected via [moonshot k3](https://www.kimi.ai/blog/kimi-k3) Publisher reference Referenced by the collection source; the upstream result has not been independently captured. Benchmark [https://www.kimi.ai/blog/kimi-k3](https://www.kimi.ai/blog/kimi-k3) [Collected via](https://www.kimi.ai/blog/kimi-k3) Source Moonshot AI Original model label GLM-5.2 (max) Source version sha256:0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c Observed 2026-10-21T16:31:44.130Z Evidence SHA-256 `0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c` Source locator `/flight/sheet/data/18/scores/5` | | | | | | | | | [Arena webdev / webdev-react](https://benchize.com/benchmarks/lmarena%3Awebdev%3Awebdev-react.md) | 1,617.11 | — | 26 / 97 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1617.1107508670134 \| rating \| reported \| Higher is better \| ### Configuration category webdev-react config webdev Reasoning effort max thinkingEnabled true ### Reported statistics lower 1610.0694731910194 rank 30 upper 1624.1520285430079 variance 12.906448728115778 votes 11346 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) Source Arena Original model label GLM-5.2 (Max) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `f82507859808110820a4ab6df15561b8864137ddefc1f6fb0c552af2e58ea738` Source locator `/rows/536/row` | | | | | | | | | [Arena text style control / industry mathematical](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_mathematical.md) | 1,494.33 | — | 29 / 169 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1494.33078507462 \| rating \| reported \| Higher is better \| ### Configuration category industry_mathematical config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1482.7509047835488 rank 29 upper 1505.9106653656913 variance 34.90695431464063 votes 2786 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GLM-5.2 (Max) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/5941/row` | | | | | | | | | [Arena text style control / overall](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aoverall.md) | 1,475.99 | — | 31 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1475.9889199535698 \| rating \| reported \| Higher is better \| ### Configuration category overall config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1471.8457632331904 rank 32 upper 1480.1320766739493 variance 4.468549166049379 votes 51221 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GLM-5.2 (Max) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/31/row` | | | | | | | | | [ProgramBench / overall](https://benchize.com/benchmarks/vals-ai%3Aprogrambench%3Aoverall.md) | 63.7% | — | 6 / 6 | — | — | [Moonshot AI · sha256:0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c](https://www.kimi.ai/blog/kimi-k3) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 63.7 \| percent \| reported \| Higher is better \| ### Configuration Reasoning effort max thinkingEnabled true ### Source Score publisher [Moonshot AI](https://www.kimi.ai/blog/kimi-k3) Collected via [moonshot k3](https://www.kimi.ai/blog/kimi-k3) Publisher reference Referenced by the collection source; the upstream result has not been independently captured. Benchmark [https://www.kimi.ai/blog/kimi-k3](https://www.kimi.ai/blog/kimi-k3) [Collected via](https://www.kimi.ai/blog/kimi-k3) Source Moonshot AI Original model label GLM-5.2 (max) Source version sha256:0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c Observed 2026-10-21T16:31:44.130Z Evidence SHA-256 `0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c` Source locator `/flight/sheet/data/1/scores/5` | | | | | | | | | [Arena text style control / english](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aenglish.md) | 1,482.87 | — | 31 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1482.8671270767436 \| rating \| reported \| Higher is better \| ### Configuration category english config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1477.5952976876954 rank 32 upper 1488.1389564657916 variance 7.234799695759608 votes 20996 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GLM-5.2 (Max) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/1668/row` | | | | | | | | | [Arena text / expert](https://benchize.com/benchmarks/lmarena%3Atext%3Aexpert.md) | 1,486.76 | — | 38 / 170 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1486.7638031693252 \| rating \| reported \| Higher is better \| ### Configuration category expert config text Reasoning effort max thinkingEnabled true ### Reported statistics lower 1478.1460406336375 rank 43 upper 1495.3815657050127 variance 19.33271566557642 votes 5377 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GLM-5.2 (Max) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/2513/row` | | | | | | | | | [Arena text / industry software and it services](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_software_and_it_services.md) | 1,486.07 | — | 35 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1486.070188572577 \| rating \| reported \| Higher is better \| ### Configuration category industry_software_and_it_services config text Reasoning effort max thinkingEnabled true ### Reported statistics lower 1480.7028844522952 rank 38 upper 1491.437492692859 variance 7.499222265355337 votes 19889 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GLM-5.2 (Max) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/6738/row` | | | | | | | | | [Job Bench](https://benchize.com/benchmarks/jobbench.md) | 43.4% | — | 5 / 6 | — | — | [Moonshot AI · sha256:0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c](https://www.kimi.ai/blog/kimi-k3) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 43.4 \| percent \| reported \| Higher is better \| ### Configuration Reasoning effort max thinkingEnabled true ### Source Score publisher [Moonshot AI](https://www.kimi.ai/blog/kimi-k3) Collected via [moonshot k3](https://www.kimi.ai/blog/kimi-k3) Publisher reference Referenced by the collection source; the upstream result has not been independently captured. Benchmark [https://www.kimi.ai/blog/kimi-k3](https://www.kimi.ai/blog/kimi-k3) [Collected via](https://www.kimi.ai/blog/kimi-k3) Source Moonshot AI Original model label GLM-5.2 (max) Source version sha256:0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c Observed 2026-10-21T16:31:44.130Z Evidence SHA-256 `0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c` Source locator `/flight/sheet/data/14/scores/5` | | | | | | | | | [DECK-Bench (Internal)](https://benchize.com/benchmarks/deck-bench.md) | 68.6% | — | 4 / 6 | — | — | [Moonshot AI · sha256:0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c](https://www.kimi.ai/blog/kimi-k3) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 68.6 \| percent \| reported \| Higher is better \| ### Configuration benchmarkVisibility internal Reasoning effort max thinkingEnabled true ### Source Score publisher [Moonshot AI](https://www.kimi.ai/blog/kimi-k3) Collected via [moonshot k3](https://www.kimi.ai/blog/kimi-k3) Publisher reference Referenced by the collection source; the upstream result has not been independently captured. Benchmark [https://www.kimi.ai/blog/kimi-k3](https://www.kimi.ai/blog/kimi-k3) [Collected via](https://www.kimi.ai/blog/kimi-k3) Source Moonshot AI Original model label GLM-5.2 (max) Source version sha256:0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c Observed 2026-10-21T16:31:44.130Z Evidence SHA-256 `0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c` Source locator `/flight/sheet/data/19/scores/5` | | | | | | | | | [Arena text style control / creative writing](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Acreative_writing.md) | 1,453.88 | — | 29 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1453.8811240083 \| rating \| reported \| Higher is better \| ### Configuration category creative_writing config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1446.9163186177552 rank 35 upper 1460.8459293988449 variance 12.627628302781009 votes 10217 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GLM-5.2 (Max) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/1256/row` | | | | | | | | | [Arena text style control / spanish](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aspanish.md) | 1,478.85 | — | 17 / 155 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1478.8532644419242 \| rating \| reported \| Higher is better \| ### Configuration category spanish config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1463.0583491506131 rank 19 upper 1494.6481797332349 variance 64.94390821417291 votes 1548 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GLM-5.2 (Max) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10783/row` | | | | | | | | | [Arena text style control / multi turn](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Amulti_turn.md) | 1,476.11 | — | 38 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1476.1085564638374 \| rating \| reported \| Higher is better \| ### Configuration category multi_turn config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1468.7545257424363 rank 48 upper 1483.4625871852386 variance 14.07844529270299 votes 8108 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GLM-5.2 (Max) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/9363/row` | | | | | | | | | [DeepSWE](https://benchize.com/benchmarks/deepswe%3Av1.1.md) | 46.2% | — | 6 / 6 | — | — | [Moonshot AI · sha256:0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c](https://www.kimi.ai/blog/kimi-k3) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 46.2 \| percent \| reported \| Higher is better \| ### Configuration Reasoning effort max thinkingEnabled true ### Source Score publisher [Moonshot AI](https://www.kimi.ai/blog/kimi-k3) Collected via [moonshot k3](https://www.kimi.ai/blog/kimi-k3) Publisher reference Referenced by the collection source; the upstream result has not been independently captured. Benchmark [https://www.kimi.ai/blog/kimi-k3](https://www.kimi.ai/blog/kimi-k3) [Collected via](https://www.kimi.ai/blog/kimi-k3) Source Moonshot AI Original model label GLM-5.2 (max) Source version sha256:0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c Observed 2026-10-21T16:31:44.130Z Evidence SHA-256 `0e806bbad76dc8e8dbc899a86051e3406bdd5995fe6c6aa1b2176dde4fb28e6c` Source locator `/flight/sheet/data/0/scores/5` | | | | | | | | | [Arena text / hard prompts](https://benchize.com/benchmarks/lmarena%3Atext%3Ahard_prompts.md) | 1,480.61 | — | 35 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1480.6136375232381 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text Reasoning effort max thinkingEnabled true ### Reported statistics lower 1475.9061200580381 rank 38 upper 1485.3211549884377 variance 5.768829426409968 votes 33290 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GLM-5.2 (Max) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/3488/row` | | | | | | | | | [Arena text / polish](https://benchize.com/benchmarks/lmarena%3Atext%3Apolish.md) | 1,455.83 | — | 33 / 137 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1455.8297299169872 \| rating \| reported \| Higher is better \| ### Configuration category polish config text Reasoning effort max thinkingEnabled true ### Reported statistics lower 1435.213098621894 rank 39 upper 1476.4463612120805 variance 110.64689374465694 votes 834 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GLM-5.2 (Max) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/10186/row` | | | | | | | | | [Arena text style control / industry medicine and healthcare](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_medicine_and_healthcare.md) | 1,491.29 | — | 25 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1491.292511941212 \| rating \| reported \| Higher is better \| ### Configuration category industry_medicine_and_healthcare config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1480.9039742643376 rank 30 upper 1501.6810496180865 variance 28.09394037558321 votes 3768 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GLM-5.2 (Max) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/6342/row` | | | | | | | | | [Arena text style control / industry life and physical and social science](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_life_and_physical_and_social_science.md) | 1,497.95 | — | 26 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1497.9524757399486 \| rating \| reported \| Higher is better \| ### Configuration category industry_life_and_physical_and_social_science config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1490.8301808446565 rank 26 upper 1505.0747706352406 variance 13.205161617829827 votes 8550 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GLM-5.2 (Max) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/5523/row` | | | | | | | | | [Arena text style control / korean](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Akorean.md) | 1,441.76 | — | 26 / 144 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1441.7575090946361 \| rating \| reported \| Higher is better \| ### Configuration category korean config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1421.8778577765643 rank 30 upper 1461.637160412708 variance 102.87772301479508 votes 988 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GLM-5.2 (Max) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/8263/row` | | | | | | | | | [Arena text style control / hard prompts](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ahard_prompts.md) | 1,496.29 | — | 36 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1496.2852086726584 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts config text_style_control Reasoning effort max thinkingEnabled true ### Reported statistics lower 1491.5393276379189 rank 40 upper 1501.0310897073978 variance 5.863237860201693 votes 33290 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label GLM-5.2 (Max) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/3490/row` | | | | | | | | | [Arena text / non english](https://benchize.com/benchmarks/lmarena%3Atext%3Anon_english.md) | 1,459.18 | — | 30 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1459.182121497687 \| rating \| reported \| Higher is better \| ### Configuration category non_english config text Reasoning effort max thinkingEnabled true ### Reported statistics lower 1454.4450579488719 rank 33 upper 1463.9191850465018 variance 5.841471199593948 votes 30215 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GLM-5.2 (Max) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/9763/row` | | | | | | | | | [Arena webdev / overall](https://benchize.com/benchmarks/lmarena%3Awebdev%3Aoverall.md) | 1,604.22 | — | 26 / 107 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1604.2162197370149 \| rating \| reported \| Higher is better \| ### Configuration category overall config webdev Reasoning effort max thinkingEnabled true ### Reported statistics lower 1598.1626439288439 rank 30 upper 1610.2697955451858 variance 9.539547806125158 votes 16657 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/webdev/latest) Source Arena Original model label GLM-5.2 (Max) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `f82507859808110820a4ab6df15561b8864137ddefc1f6fb0c552af2e58ea738` Source locator `/rows/29/row` | | | | | | | | | [Arena text / russian](https://benchize.com/benchmarks/lmarena%3Atext%3Arussian.md) | 1,467.91 | — | 32 / 172 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1467.9071748109147 \| rating \| reported \| Higher is better \| ### Configuration category russian config text Reasoning effort max thinkingEnabled true ### Reported statistics lower 1459.7442775916893 rank 34 upper 1476.0700720301402 variance 17.345725705214907 votes 6017 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GLM-5.2 (Max) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/10417/row` | | | | | | | | | [Arena text / instruction following](https://benchize.com/benchmarks/lmarena%3Atext%3Ainstruction_following.md) | 1,466.12 | — | 32 / 173 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1466.1240960287787 \| rating \| reported \| Higher is better \| ### Configuration category instruction_following config text Reasoning effort max thinkingEnabled true ### Reported statistics lower 1460.5434069593764 rank 35 upper 1471.704785098181 variance 8.107360235536289 votes 17693 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label GLM-5.2 (Max) Observed 2026-10-22T06:45:03.380Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/7568/row` | | | | | | | | --- Cite as: GLM-5.2Max — Benchize, https://benchize.com/models/glm-5-2-max (retrieved 2026-10-22)