# GLM-5.2 > Source: Benchize (https://benchize.com) — https://benchize.com/models/glm-5-2. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/glm-5-2. Z.ai Canonical URL: https://benchize.com/models/glm-5-2 Last updated: Wed, 21 Oct 2026 18:52:20 GMT Reproduction and quotation must name Benchize, link to the canonical HTML URL, and retain individual source citations. Z.ai ## Benchmarks | Benchmark | Score | ± | Rank | Cost | Source | | | --- | --- | --- | --- | --- | --- | --- | | [Apex](https://benchize.com/benchmarks/matharena%3Aapex--apex_2025.md) | 19.79% | 95% CI 11.82–27.76% | 12 / 30 | 0.18usd per problem | [matharena · apex--apex_2025](https://matharena.ai/competition_tables/apex--apex_2025) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 19.79 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.18 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition apex--apex_2025 predicted false sourceModelName GLM 5.2 sourceModelVersion glm/glm-52 ### Reported statistics Uncertainty 95% confidence interval: 11.82–27.76% confidenceInterval95 7.97 problems 12 ### Source [Original source](https://matharena.ai/competition_tables/apex--apex_2025) Source matharena Original model label GLM 5.2 Source version apex--apex_2025 Observed 2026-10-21T16:52:38.728Z Evidence SHA-256 `20b28370d9d7f5a15a19fc9e4226c9857cdb07bc42b32ccec508e687b7b9f3fc` Source locator `/table/rows/14` | | | | | | | | [BrokenArXiv 02/2026](https://benchize.com/benchmarks/matharena%3Aarxiv_false--february.md) | 10.48% | 95% CI 2.85–18.11% | 11 / 15 | 0.14usd per problem | [matharena · arxiv_false--february](https://matharena.ai/competition_tables/arxiv_false--february) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 10.48 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.14 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition arxiv_false--february predicted false sourceModelName GLM 5.2 sourceModelVersion glm/glm-52 ### Reported statistics Uncertainty 95% confidence interval: 2.85–18.11% confidenceInterval95 7.63 problems 31 ### Source [Original source](https://matharena.ai/competition_tables/arxiv_false--february) Source matharena Original model label GLM 5.2 Source version arxiv_false--february Observed 2026-10-21T16:52:23.532Z Evidence SHA-256 `a6bc6fc18da7dd181ed727da924f9569d3e323c31c1aba9a4d9fa3bff492bee3` Source locator `/table/rows/11` | | | | | | | | [LiveBench](https://benchize.com/benchmarks/livebench%3Atasks.md) | 98% | — | 1 / 10 | — | [LiveBench](https://api.github.com/repos/LiveBench/livebench.github.io/contents/public/table_2026_06_25.csv?ref=19e766a5de4de07d672ed5bf9f0a69ceed1d39bf) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `AMPS_Hard` \| 98 \| percent \| reported \| Higher is better \| \| `code_completion` \| 80.435 \| percent \| reported \| Higher is better \| \| `code_generation` \| 78.873 \| percent \| reported \| Higher is better \| \| `connections` \| 94 \| percent \| reported \| Higher is better \| \| `consecutive_events` \| 79.276 \| percent \| reported \| Higher is better \| \| `integrals_with_game` \| 76 \| percent \| reported \| Higher is better \| \| `javascript` \| 59.091 \| percent \| reported \| Higher is better \| \| `logic_with_navigation` \| 80 \| percent \| reported \| Higher is better \| \| `math_comp` \| 96.078 \| percent \| reported \| Higher is better \| \| `olympiad` \| 89.047 \| percent \| reported \| Higher is better \| \| `paraphrase` \| 62.25 \| percent \| reported \| Higher is better \| \| `plot_unscrambling` \| 60.725 \| percent \| reported \| Higher is better \| \| `python` \| 50 \| percent \| reported \| Higher is better \| \| `simplify` \| 55.667 \| percent \| reported \| Higher is better \| \| `spatial` \| 94 \| percent \| reported \| Higher is better \| \| `story_generation` \| 62.883 \| percent \| reported \| Higher is better \| \| `summarize` \| 68.367 \| percent \| reported \| Higher is better \| \| `tablejoin` \| 45.865 \| percent \| reported \| Higher is better \| \| `tablereformat` \| 96.078 \| percent \| reported \| Higher is better \| \| `theory_of_mind` \| 75 \| percent \| reported \| Higher is better \| \| `typescript` \| 46.667 \| percent \| reported \| Higher is better \| \| `typos` \| 74 \| percent \| reported \| Higher is better \| \| `zebra_puzzle` \| 65.5 \| percent \| reported \| Higher is better \| ### Configuration Model configuration glm-5.2 sourceRelease 2026_06_25 ### Source [Original source](https://api.github.com/repos/LiveBench/livebench.github.io/contents/public/table_2026_06_25.csv?ref=19e766a5de4de07d672ed5bf9f0a69ceed1d39bf) Source LiveBench Original model label glm-5.2 Observed 2026-10-21T16:40:05.068Z Evidence SHA-256 `f0330164423abf9803631fc5b2f2b5427f17c0161c12e15021bb0f9781d2afa8` Source locator `/rows/11` | | | | | | | | [ARC-AGI-1](https://benchize.com/benchmarks/arc-prize%3Av1_Semi_Private.md) | 77% | — | 96 / 213 | 0.19usd per task | [arc prize · v1](https://arcprize.org/media/data/leaderboard/v1.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.77 \| score_fraction \| v1_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.1916 \| usd_per_task \| v1_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v1_Semi_Private harness Not reported modelGroup Not reported modelType CoT sourceModelVersion glm-5.2 ### Source [Original source](https://arcprize.org/media/data/leaderboard/v1.json) Source arc prize Original model label GLM-5.2 Source version v1 Observed 2026-10-21T16:34:20.378Z Evidence SHA-256 `302d8267c0522bf450ec1deeac4d060e2cf2fb444ba0a4269014d9535de0bd1f` Source locator `/evaluations/169` | | | | | | | | [BrokenArXiv 05/2026](https://benchize.com/benchmarks/matharena%3Aarxiv_false--may.md) | 10.5% | 95% CI 4.49–16.51% | 16 / 20 | 0.14usd per problem | [matharena · arxiv_false--may](https://matharena.ai/competition_tables/arxiv_false--may) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 10.50 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.14 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition arxiv_false--may predicted false sourceModelName GLM 5.2 sourceModelVersion glm/glm-52 ### Reported statistics Uncertainty 95% confidence interval: 4.49–16.51% confidenceInterval95 6.01 problems 50 ### Source [Original source](https://matharena.ai/competition_tables/arxiv_false--may) Source matharena Original model label GLM 5.2 Source version arxiv_false--may Observed 2026-10-21T16:52:24.785Z Evidence SHA-256 `b317fca30109e8c78ed5d2b835fe227b8cfbee3b6f9cb6d7aaeadca866660969` Source locator `/table/rows/18` | | | | | | | | [ArXivMath 06/2026](https://benchize.com/benchmarks/matharena%3Aarxiv--june.md) | 46.53% | 95% CI 38.38–54.68% | 19 / 22 | 0.22usd per problem | [matharena · arxiv--june](https://matharena.ai/competition_tables/arxiv--june) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 46.53 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.22 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition arxiv--june predicted false sourceModelName GLM 5.2 sourceModelVersion glm/glm-52 ### Reported statistics Uncertainty 95% confidence interval: 38.38–54.68% confidenceInterval95 8.15 problems 48 ### Source [Original source](https://matharena.ai/competition_tables/arxiv--june) Source matharena Original model label GLM 5.2 Source version arxiv--june Observed 2026-10-21T16:52:29.905Z Evidence SHA-256 `6832faff9be7e16a6c646c59017e30a2caedebe8cf02caf617a5ed9d8fb03bab` Source locator `/table/rows/25` | | | | | | | | [AIME 2026](https://benchize.com/benchmarks/aime-2026.md) | 90% | 95% CI 82.41–97.59% | 21 / 21 | 0.08usd per problem | [matharena · aime--aime_2026](https://matharena.ai/competition_tables/aime--aime_2026) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 90.00 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.076 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition aime--aime_2026 predicted false sourceModelName GLM 5.2 sourceModelVersion glm/glm-52 ### Reported statistics Uncertainty 95% confidence interval: 82.41–97.59% confidenceInterval95 7.59 problems 30 ### Source [Original source](https://matharena.ai/competition_tables/aime--aime_2026) Source matharena Original model label GLM 5.2 Source version aime--aime_2026 Observed 2026-10-21T16:52:37.816Z Evidence SHA-256 `58b3ac1e0805975eba566c493b8e0165d41eb7ca517218106e112529fb6342de` Source locator `/table/rows/27` | | | | | | | | [ArXivMath 02/2026](https://benchize.com/benchmarks/matharena%3Aarxiv--february.md) | 46.09% | 95% CI 37.45–54.73% | 8 / 20 | 0.25usd per problem | [matharena · arxiv--february](https://matharena.ai/competition_tables/arxiv--february) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 46.09 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.25 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition arxiv--february predicted false sourceModelName GLM 5.2 sourceModelVersion glm/glm-52 ### Reported statistics Uncertainty 95% confidence interval: 37.45–54.73% confidenceInterval95 8.64 problems 32 ### Source [Original source](https://matharena.ai/competition_tables/arxiv--february) Source matharena Original model label GLM 5.2 Source version arxiv--february Observed 2026-10-21T16:52:27.963Z Evidence SHA-256 `3bc5b0a1eb91a0bdaa3d0942ebf82327a8664334b225ae3b2dc1d8b4f57efa51` Source locator `/table/rows/7` | | | | | | | | [ARC-AGI-2](https://benchize.com/benchmarks/arc-prize%3Av2_Semi_Private.md) | 22.78% | — | 108 / 212 | 0.25usd per task | [arc prize · v2](https://arcprize.org/media/data/leaderboard/v2.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.22775 \| score_fraction \| v2_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.2501 \| usd_per_task \| v2_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v2_Semi_Private harness Not reported modelGroup Not reported modelType CoT sourceModelVersion glm-5.2 ### Source [Original source](https://arcprize.org/media/data/leaderboard/v2.json) Source arc prize Original model label GLM-5.2 Source version v2 Observed 2026-10-21T16:34:20.750Z Evidence SHA-256 `bca68e12cc9a01954ae21b641844c1ecbabe146cb24b87f0f8e9b1db27433c29` Source locator `/evaluations/171` | | | | | | | | [ArXivMath 03/2026](https://benchize.com/benchmarks/matharena%3Aarxiv--march.md) | 61.67% | 95% CI 52.97–70.37% | 6 / 14 | 0.21usd per problem | [matharena · arxiv--march](https://matharena.ai/competition_tables/arxiv--march) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 61.67 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.21 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition arxiv--march predicted false sourceModelName GLM 5.2 sourceModelVersion glm/glm-52 ### Reported statistics Uncertainty 95% confidence interval: 52.97–70.37% confidenceInterval95 8.70 problems 30 ### Source [Original source](https://matharena.ai/competition_tables/arxiv--march) Source matharena Original model label GLM 5.2 Source version arxiv--march Observed 2026-10-21T16:52:28.322Z Evidence SHA-256 `9cb6d9cc26949fcb2b6affed792584b4bfe9d6168e1fc5cf2c13b38d3479715b` Source locator `/table/rows/5` | | | | | | | | [BrokenArXiv 03/2026](https://benchize.com/benchmarks/matharena%3Aarxiv_false--march.md) | 12.05% | 95% CI 6.02–18.08% | 8 / 14 | 0.13usd per problem | [matharena · arxiv_false--march](https://matharena.ai/competition_tables/arxiv_false--march) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 12.05 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.13 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition arxiv_false--march predicted false sourceModelName GLM 5.2 sourceModelVersion glm/glm-52 ### Reported statistics Uncertainty 95% confidence interval: 6.02–18.08% confidenceInterval95 6.03 problems 56 ### Source [Original source](https://matharena.ai/competition_tables/arxiv_false--march) Source matharena Original model label GLM 5.2 Source version arxiv_false--march Observed 2026-10-21T16:52:24.043Z Evidence SHA-256 `b2ea8c773acad8b54736938938d6ee37fa533bfc5b985eefc303733bfcb0c6f0` Source locator `/table/rows/9` | | | | | | | | [ArXivLean 06/2026](https://benchize.com/benchmarks/matharena%3Aarxivlean--june.md) | 8.7% | 95% CI 0.56–16.84% | 9 / 10 | 7.86usd per problem | [matharena · arxivlean--june](https://matharena.ai/competition_tables/arxivlean--june) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 8.70 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 7.86 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition arxivlean--june predicted false sourceModelName GLM 5.2 sourceModelVersion glm/glm-52 ### Reported statistics Uncertainty 95% confidence interval: 0.56–16.84% confidenceInterval95 8.14 problems 46 ### Source [Original source](https://matharena.ai/competition_tables/arxivlean--june) Source matharena Original model label GLM 5.2 Source version arxivlean--june Observed 2026-10-21T16:52:22.483Z Evidence SHA-256 `0869c2556b20f1879eb0ea99ea8151e805471cd9d6be57c652f764a775491b7d` Source locator `/table/rows/12` | | | | | | | | [Apex Shortlist](https://benchize.com/benchmarks/matharena%3Aapex--shortlist_2025.md) | 68.09% | 95% CI 61.43–74.75% | 16 / 24 | 0.16usd per problem | [matharena · apex--shortlist_2025](https://matharena.ai/competition_tables/apex--shortlist_2025) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 68.09 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.16 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition apex--shortlist_2025 predicted false sourceModelName GLM 5.2 sourceModelVersion glm/glm-52 ### Reported statistics Uncertainty 95% confidence interval: 61.43–74.75% confidenceInterval95 6.66 problems 47 ### Source [Original source](https://matharena.ai/competition_tables/apex--shortlist_2025) Source matharena Original model label GLM 5.2 Source version apex--shortlist_2025 Observed 2026-10-21T16:52:39.300Z Evidence SHA-256 `74513abecacb4d230d741f4d6df425ce878fb450220e88a1a6823524476c2989` Source locator `/table/rows/18` | | | | | | | | [BrokenArXiv 06/2026](https://benchize.com/benchmarks/matharena%3Aarxiv_false--june.md) | 14.2% | 95% CI 8.83–19.57% | 18 / 21 | 0.14usd per problem | [matharena · arxiv_false--june](https://matharena.ai/competition_tables/arxiv_false--june) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 14.20 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.14 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition arxiv_false--june predicted false sourceModelName GLM 5.2 sourceModelVersion glm/glm-52 ### Reported statistics Uncertainty 95% confidence interval: 8.83–19.57% confidenceInterval95 5.37 problems 54 ### Source [Original source](https://matharena.ai/competition_tables/arxiv_false--june) Source matharena Original model label GLM 5.2 Source version arxiv_false--june Observed 2026-10-21T16:52:25.323Z Evidence SHA-256 `f6d7e2280d05706643d46ae7786bd3fad6d912e4893781c3f62c73deebf38459` Source locator `/table/rows/24` | | | | | | | | [ArXivMath 05/2026](https://benchize.com/benchmarks/matharena%3Aarxiv--may.md) | 56.67% | 95% CI 47.8–65.54% | 13 / 21 | 0.22usd per problem | [matharena · arxiv--may](https://matharena.ai/competition_tables/arxiv--may) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 56.67 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.22 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition arxiv--may predicted false sourceModelName GLM 5.2 sourceModelVersion glm/glm-52 ### Reported statistics Uncertainty 95% confidence interval: 47.8–65.54% confidenceInterval95 8.87 problems 40 ### Source [Original source](https://matharena.ai/competition_tables/arxiv--may) Source matharena Original model label GLM 5.2 Source version arxiv--may Observed 2026-10-21T16:52:29.369Z Evidence SHA-256 `758e1bba77e36f4ced2a51b4bc0d46bd956ed94ef6f57e93e1a974b75e76a4ce` Source locator `/table/rows/15` | | | | | | | | [ArXivMath 04/2026](https://benchize.com/benchmarks/matharena%3Aarxiv--april.md) | 47.5% | 95% CI 38.57–56.43% | 14 / 19 | 0.2usd per problem | [matharena · arxiv--april](https://matharena.ai/competition_tables/arxiv--april) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 47.50 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.20 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition arxiv--april predicted false sourceModelName GLM 5.2 sourceModelVersion glm/glm-52 ### Reported statistics Uncertainty 95% confidence interval: 38.57–56.43% confidenceInterval95 8.93 problems 40 ### Source [Original source](https://matharena.ai/competition_tables/arxiv--april) Source matharena Original model label GLM 5.2 Source version arxiv--april Observed 2026-10-21T16:52:28.840Z Evidence SHA-256 `5139c835884bfab38f18d23a248814af4680927310bc5cd2a86ea2eab779e0a7` Source locator `/table/rows/15` | | | | | | | | [EQ-Bench 4](https://benchize.com/benchmarks/eq-bench%3Aeqbench4.md) | 1,221.9elo | CI 1,212.7–1,231.4 | 14 / 26 | — | [eq bench · eqbench4](https://eqbench.com/eqbench4/eqbench4_data.js) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1221.9 \| elo \| overall \| Higher is better \| ### Configuration protocol eqbench4 ### Reported statistics Uncertainty Confidence interval: 1,212.7–1,231.4 confidenceIntervalHigh 1231.4 confidenceIntervalLow 1212.7 scenarios 120 ### Source [Original source](https://eqbench.com/eqbench4/eqbench4_data.js) Source eq bench Original model label glm-5.2 Source version eqbench4 Observed 2026-10-21T16:35:00.261Z Evidence SHA-256 `188d8ea4a393978063a6c24dff6c92ce185169827038bfa558091212a68c29d8` Source locator `/models/13` | | | | | | | | [HMMT Feb 2026](https://benchize.com/benchmarks/matharena%3Ahmmt--hmmt_feb_2026.md) | 92.42% | 95% CI 86.04–98.8% | 11 / 21 | 0.1usd per problem | [matharena · hmmt--hmmt_feb_2026](https://matharena.ai/competition_tables/hmmt--hmmt_feb_2026) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 92.42 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.10 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition hmmt--hmmt_feb_2026 predicted false sourceModelName GLM 5.2 sourceModelVersion glm/glm-52 ### Reported statistics Uncertainty 95% confidence interval: 86.04–98.8% confidenceInterval95 6.38 problems 33 ### Source [Original source](https://matharena.ai/competition_tables/hmmt--hmmt_feb_2026) Source matharena Original model label GLM 5.2 Source version hmmt--hmmt_feb_2026 Observed 2026-10-21T16:52:38.351Z Evidence SHA-256 `0dce922c33a54d29d4a1872a42d74077b491915c80d8433f4b379ea0b78bb979` Source locator `/table/rows/12` | | | | | | | | [BrokenArXiv 04/2026](https://benchize.com/benchmarks/matharena%3Aarxiv_false--april.md) | 18.44% | 95% CI 11.56–25.32% | 13 / 17 | 0.14usd per problem | [matharena · arxiv_false--april](https://matharena.ai/competition_tables/arxiv_false--april) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 18.44 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.14 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition arxiv_false--april predicted false sourceModelName GLM 5.2 sourceModelVersion glm/glm-52 ### Reported statistics Uncertainty 95% confidence interval: 11.56–25.32% confidenceInterval95 6.88 problems 61 ### Source [Original source](https://matharena.ai/competition_tables/arxiv_false--april) Source matharena Original model label GLM 5.2 Source version arxiv_false--april Observed 2026-10-21T16:52:24.402Z Evidence SHA-256 `e543f14dac0ba9663e8104a87738726c9848b89171a53fdca89b7baa4a892399` Source locator `/table/rows/14` | | | | | | | | [Vending-Bench 2](https://benchize.com/benchmarks/vendingbench%3Av2.md) | — | — | — | $8,313.78 | [vendingbench](https://andonlabs.com/_app/immutable/chunks/Cjn0_qj9.js) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `final_balance` \| 8313.778333333335 \| USD \| one_simulated_year \| Higher is better \| \| `geometric_mean_balance` \| 7988.294096269425 \| USD \| positive_final_balances \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration GLM-5.2 thinkingEnabled Not reported ### Reported statistics confidenceHalfWidth95 2124.8483546620396 positiveBalanceRuns 6 runCount 6 standardDeviation 2655.507270262438 standardError 1084.106303399 ### Source [Original source](https://andonlabs.com/_app/immutable/chunks/Cjn0_qj9.js) Source vendingbench Original model label GLM-5.2 Observed 2026-10-21T16:36:40.592Z Evidence SHA-256 `1a0b043147050298c405bcb743d73e425d532464202231cd18c27f836fa5f223` Source locator `/rows/24` | | | | | | | | [SimpleBench](https://benchize.com/benchmarks/simplebench%3Aavg-at-5.md) | 58.8% | — | 27 / 62 | — | [simplebench](https://simple-bench.com/static/js/leaderboard-data.js) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 58.8 \| percent \| average_at_5 \| Higher is better \| ### Configuration Reasoning effort unknown Model configuration GLM 5.2 thinkingEnabled Not reported ### Reported statistics rank 41st ### Source [Original source](https://simple-bench.com/static/js/leaderboard-data.js) Source simplebench Original model label GLM 5.2 Observed 2026-10-21T16:32:13.183Z Evidence SHA-256 `b2d0285ad3e4e15750ed20d39897e7558d1c05e8962e90c861b06f93c8019dc9` Source locator `/rows/42` | | | | | | | | [ArXivMath Overall](https://benchize.com/benchmarks/matharena%3Aoverall--final_answer_comps.md) | 67.58% | 95% CI 63.99–71.17% | 13 / 20 | 0.12usd per problem | [matharena · overall--final_answer_comps](https://matharena.ai/competition_tables/overall--final_answer_comps) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 67.58 \| percent \| competition \| Higher is better \| \| `cost_per_problem` \| 0.12 \| usd_per_problem \| competition \| Lower is better \| ### Configuration competition overall--final_answer_comps predicted false sourceModelName GLM 5.2 sourceModelVersion glm/glm-52 ### Reported statistics Uncertainty 95% confidence interval: 63.99–71.17% confidenceInterval95 3.59 problems Not reported ### Source [Original source](https://matharena.ai/competition_tables/overall--final_answer_comps) Source matharena Original model label GLM 5.2 Source version overall--final_answer_comps Observed 2026-10-21T16:52:34.395Z Evidence SHA-256 `8b08b20c1ac5aec9a829d234469bc39d40b0eb189790d84b7264c2756ffa161e` Source locator `/table/rows/15` | | | | | | | --- Cite as: GLM-5.2 — Benchize, https://benchize.com/models/glm-5-2 (retrieved 2026-10-21)