--- title: "hermes \u00b7 GLM 5.1 | Pelican benchmark" url: https://evaljetty.com/pelicans/runs/agents/hermes-glm51.html description: "hermes \u00b7 GLM 5.1 (openrouter/z-ai/glm-5.1) drawing a pelican riding a bicycle: every hill-climb run with self-scores, external judge scores and Jetty trajectories." updated: 2026-09-28 publisher: Jetty (https://jetty.io) --- 02 — Runs · v1 · jettyio · auto-evolved runbook (weakest-axis targeting) # hermes openrouter/z-ai/glm-5.1 Zhipu's GLM 5.1. The steadiest v1 climber: 24, 30, 35, 36.5 with no grade inflation. Judge, best round 27.3/40 round v2 (agent's pick) Self-score 36.5/40 inflation +9.2 Runs 10 not recorded (v1) ![hermes · GLM 5.1 best round](https://evaljetty.com/pelicans/img/hermes-glm51/v2.svg) best round v2 · 4b324d80 ### Self-score vs judge, by axis Best round v2, 0–10 per axis agent self-scoreexternal judge **Judge:** The bicycle is solid, with spoked wheels, a red frame, handlebars, a seat and chain. The pelican sits on the seat with its orange legs reaching the pedals and its wing extended toward the handlebars. The weakest part is the pelican's head: the throat pouch is a huge orange blob hanging off the neck rather than under the beak, which makes the anatomy odd. The wing rendering is also somewhat messy, with stray overlapping feather shapes near the handlebars. ### Score by round Out of 40. Each round starts from the previous round's best SVG. Dashed line: the 28/40 pass threshold. self-scorejudgepass ≥ 28 ## 10 drawings, *oldest first.* Click a drawing to open it in the head-to-head viewer. The outlined card is the agent's best round. Verdicts are derived (code checks on the stored SVG and judge ≥ 28/40); see [Runs](https://evaljetty.com/pelicans/runs/index.html#all-runs). [![hermes · GLM 5.1 round v1](https://evaljetty.com/pelicans/img/hermes-glm51/v1.svg)](https://evaljetty.com/pelicans/investigations/best-pelican.html#hermes-glm51/v1) **v1** passjudge **28.7** · self 32 c1f2da04[runbook](https://evaljetty.com/pelicans/author/versions.html#hermes-glm51/v1) [![hermes · GLM 5.1 round v2](https://evaljetty.com/pelicans/img/hermes-glm51/v2.svg)](https://evaljetty.com/pelicans/investigations/best-pelican.html#hermes-glm51/v2) **v2** · best failjudge **27.3** · self 36.5 4b324d80[runbook](https://evaljetty.com/pelicans/author/versions.html#hermes-glm51/v2) [![hermes · GLM 5.1 round v3](https://evaljetty.com/pelicans/img/hermes-glm51/v3.svg)](https://evaljetty.com/pelicans/investigations/best-pelican.html#hermes-glm51/v3) **v3** passjudge **28.8** · self 36 f443b217[runbook](https://evaljetty.com/pelicans/author/versions.html#hermes-glm51/v3) [![hermes · GLM 5.1 round v4](https://evaljetty.com/pelicans/img/hermes-glm51/v4.svg)](https://evaljetty.com/pelicans/investigations/best-pelican.html#hermes-glm51/v4) **v4** passjudge **28.7** · self 33 7ce1468b[runbook](https://evaljetty.com/pelicans/author/versions.html#hermes-glm51/v4) [![hermes · GLM 5.1 round v5](https://evaljetty.com/pelicans/img/hermes-glm51/v5.svg)](https://evaljetty.com/pelicans/investigations/best-pelican.html#hermes-glm51/v5) **v5** failjudge **27.7** · self 33 ab8cb01d[runbook](https://evaljetty.com/pelicans/author/versions.html#hermes-glm51/v5) [![hermes · GLM 5.1 round v6](https://evaljetty.com/pelicans/img/hermes-glm51/v6.svg)](https://evaljetty.com/pelicans/investigations/best-pelican.html#hermes-glm51/v6) **v6** failjudge **25.7** · self 34.5 9fd19804[runbook](https://evaljetty.com/pelicans/author/versions.html#hermes-glm51/v6) [![hermes · GLM 5.1 round v7](https://evaljetty.com/pelicans/img/hermes-glm51/v7.svg)](https://evaljetty.com/pelicans/investigations/best-pelican.html#hermes-glm51/v7) **v7** failjudge **25** · self 36 83e8efe2[runbook](https://evaljetty.com/pelicans/author/versions.html#hermes-glm51/v7) [![hermes · GLM 5.1 round v8](https://evaljetty.com/pelicans/img/hermes-glm51/v8.svg)](https://evaljetty.com/pelicans/investigations/best-pelican.html#hermes-glm51/v8) **v8** failjudge **24.7** · self 34 21b9b8c1[runbook](https://evaljetty.com/pelicans/author/versions.html#hermes-glm51/v8) [![hermes · GLM 5.1 round v9](https://evaljetty.com/pelicans/img/hermes-glm51/v9.svg)](https://evaljetty.com/pelicans/investigations/best-pelican.html#hermes-glm51/v9) **v9** failjudge **24.2** · self 33 9f9e50be[runbook](https://evaljetty.com/pelicans/author/versions.html#hermes-glm51/v9) [![hermes · GLM 5.1 round v10](https://evaljetty.com/pelicans/img/hermes-glm51/v10.svg)](https://evaljetty.com/pelicans/investigations/best-pelican.html#hermes-glm51/v10) **v10** failjudge **25.7** · self 36.5 fff60669[runbook](https://evaljetty.com/pelicans/author/versions.html#hermes-glm51/v10) ### Scores per round | Round | Pelican | Bicycle | Composition | Polish | Self total | Judge total | Verdict | Judge spread | Cost | Minutes | Trajectory | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | v1 | 7self 8 | 7.2self 8 | 7.5self 8 | 7self 8 | 32 | 28.7 | pass | 0.5 | – | – | c1f2da04 | | v2 | 6.5self 9.5 | 7.3self 9.5 | 7self 8.5 | 6.5self 9 | 36.5 | 27.3 | fail | 0.5 | – | – | 4b324d80 | | v3 | 7self 9 | 7.3self 8 | 7.5self 10 | 7self 9 | 36 | 28.8 | pass | 0.5 | – | – | f443b217 | | v4 | 7self 8 | 7.2self 9 | 7.5self 8 | 7self 8 | 33 | 28.7 | pass | 3.5 | – | – | 7ce1468b | | v5 | 6.3self 9 | 7.3self 8 | 7.2self 8 | 6.8self 8 | 33 | 27.7 | fail | 0.5 | – | – | ab8cb01d | | v6 | 5.8self 8.5 | 7self 9.5 | 6.7self 8.5 | 6.2self 8 | 34.5 | 25.7 | fail | 3.5 | – | – | 9fd19804 | | v7 | 5.5self 9 | 7self 9 | 6.5self 9 | 6self 9 | 36 | 25 | fail | 0 | – | – | 83e8efe2 | | v8 | 5.5self 9 | 7self 8 | 6self 9 | 6.2self 8 | 34 | 24.7 | fail | 0.5 | – | – | 21b9b8c1 | | v9 | 5.5self 8 | 7self 9 | 5.7self 8 | 6self 8 | 33 | 24.2 | fail | 0.5 | – | – | 9f9e50be | | v10 | 6self 9.5 | 7.2self 9 | 6.2self 9 | 6.3self 9 | 36.5 | 25.7 | fail | 1.5 | – | – | fff60669 | --- Source: https://evaljetty.com/pelicans/runs/agents/hermes-glm51.html · Evals by Jetty · Run your own evals: https://jetty.io/?utm_source=evaljetty&utm_medium=llms