--- title: "hermes \u00b7 Gemini 3.5 Flash | Pelican benchmark" url: https://evaljetty.com/pelicans/agents/hermes-flash.html description: "hermes \u00b7 Gemini 3.5 Flash (openrouter/google/gemini-3.5-flash) drawing a pelican riding a bicycle: every hill-climb round, self-scores and external judge scores." updated: 2026-09-28 publisher: Jetty (https://jetty.io) --- v1 · May 2026 · jettyio · auto-evolved runbook (weakest-axis targeting) # hermes · Gemini 3.5 Flash Same hermes agent, Sonnet swapped for Flash: +5 self-score points from the model alone. agent **hermes** · model **openrouter/google/gemini-3.5-flash** Judge, best round 28.2/40 round v9 Self-score, best round 39.5/40 inflation +11.3 Rounds 10 Jetty trajectories ![hermes · Gemini 3.5 Flash best round](https://evaljetty.com/pelicans/img/hermes-flash/v9.svg) best round v9 · [e6d4548b ↗](https://jetty.io/jettyio/pelican-bicycle-svg/e6d4548b) ### Self-score vs judge, by axis Best round v9, 0–10 per axis agent self-scoreexternal judge **Judge:** The bicycle is well formed, with spoked wheels, chain, crank, fenders and a fish crate, set against an attractive seaside backdrop. The pelican's anatomy is confused: the huge orange pouch reads as a detached sheet, the head is tiny and tilted back, the body is a jumble of white blobs with an odd grey tail, and the feet only loosely meet the pedals. ### Score by round Out of 40. Each round starts from the previous round's best SVG. self-scorejudge ## Every round Click a drawing to open it in the head-to-head viewer. The outlined card is the agent's best round. [![hermes · Gemini 3.5 Flash round v1](https://evaljetty.com/pelicans/img/hermes-flash/v1.svg)](https://evaljetty.com/pelicans/head-to-head.html#hermes-flash/v1) **v1**judge **28.5** · self 39 [c118fb80 ↗](https://jetty.io/jettyio/pelican-bicycle-svg/c118fb80)[runbook](https://evaljetty.com/pelicans/runbooks.html#hermes-flash/v1) [![hermes · Gemini 3.5 Flash round v2](https://evaljetty.com/pelicans/img/hermes-flash/v2.svg)](https://evaljetty.com/pelicans/head-to-head.html#hermes-flash/v2) **v2**judge **28.2** · self 38 [2128ffc1 ↗](https://jetty.io/jettyio/pelican-bicycle-svg/2128ffc1)[runbook](https://evaljetty.com/pelicans/runbooks.html#hermes-flash/v2) [![hermes · Gemini 3.5 Flash round v3](https://evaljetty.com/pelicans/img/hermes-flash/v3.svg)](https://evaljetty.com/pelicans/head-to-head.html#hermes-flash/v3) **v3**judge **26.5** · self 37 [2405db86 ↗](https://jetty.io/jettyio/pelican-bicycle-svg/2405db86)[runbook](https://evaljetty.com/pelicans/runbooks.html#hermes-flash/v3) [![hermes · Gemini 3.5 Flash round v4](https://evaljetty.com/pelicans/img/hermes-flash/v4.svg)](https://evaljetty.com/pelicans/head-to-head.html#hermes-flash/v4) **v4**judge **28.7** · self 39 [822a3bca ↗](https://jetty.io/jettyio/pelican-bicycle-svg/822a3bca)[runbook](https://evaljetty.com/pelicans/runbooks.html#hermes-flash/v4) [![hermes · Gemini 3.5 Flash round v5](https://evaljetty.com/pelicans/img/hermes-flash/v5.svg)](https://evaljetty.com/pelicans/head-to-head.html#hermes-flash/v5) **v5**judge **30** · self 38.8 [60502506 ↗](https://jetty.io/jettyio/pelican-bicycle-svg/60502506)[runbook](https://evaljetty.com/pelicans/runbooks.html#hermes-flash/v5) [![hermes · Gemini 3.5 Flash round v6](https://evaljetty.com/pelicans/img/hermes-flash/v6.svg)](https://evaljetty.com/pelicans/head-to-head.html#hermes-flash/v6) **v6**judge **26.8** · self 38 [2c2a74e8 ↗](https://jetty.io/jettyio/pelican-bicycle-svg/2c2a74e8)[runbook](https://evaljetty.com/pelicans/runbooks.html#hermes-flash/v6) [![hermes · Gemini 3.5 Flash round v7](https://evaljetty.com/pelicans/img/hermes-flash/v7.svg)](https://evaljetty.com/pelicans/head-to-head.html#hermes-flash/v7) **v7**judge **27** · self 38.5 [c165de92 ↗](https://jetty.io/jettyio/pelican-bicycle-svg/c165de92)[runbook](https://evaljetty.com/pelicans/runbooks.html#hermes-flash/v7) [![hermes · Gemini 3.5 Flash round v8](https://evaljetty.com/pelicans/img/hermes-flash/v8.svg)](https://evaljetty.com/pelicans/head-to-head.html#hermes-flash/v8) **v8**judge **26.3** · self 38 [d391e018 ↗](https://jetty.io/jettyio/pelican-bicycle-svg/d391e018)[runbook](https://evaljetty.com/pelicans/runbooks.html#hermes-flash/v8) [![hermes · Gemini 3.5 Flash round v9](https://evaljetty.com/pelicans/img/hermes-flash/v9.svg)](https://evaljetty.com/pelicans/head-to-head.html#hermes-flash/v9) **v9** · bestjudge **28.2** · self 39.5 [e6d4548b ↗](https://jetty.io/jettyio/pelican-bicycle-svg/e6d4548b)[runbook](https://evaljetty.com/pelicans/runbooks.html#hermes-flash/v9) [![hermes · Gemini 3.5 Flash round v10](https://evaljetty.com/pelicans/img/hermes-flash/v10.svg)](https://evaljetty.com/pelicans/head-to-head.html#hermes-flash/v10) **v10**judge **26.5** · self 38.5 [3e21bf05 ↗](https://jetty.io/jettyio/pelican-bicycle-svg/3e21bf05)[runbook](https://evaljetty.com/pelicans/runbooks.html#hermes-flash/v10) ### Scores per round | Round | Pelican | Bicycle | Composition | Polish | Self total | Judge total | Judge spread | Minutes | Trajectory | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | v1 | 7self 10 | 7.5self 9.5 | 6.8self 10 | 7.2self 9.5 | 39 | 28.5 | 1 | – | [c118fb80 ↗](https://jetty.io/jettyio/pelican-bicycle-svg/c118fb80) | | v2 | 7self 9 | 7.8self 10 | 6.3self 9 | 7self 10 | 38 | 28.2 | 1 | – | [2128ffc1 ↗](https://jetty.io/jettyio/pelican-bicycle-svg/2128ffc1) | | v3 | 6.3self 9.5 | 7.3self 9 | 6.3self 9.5 | 6.5self 9.5 | 37 | 26.5 | 0 | – | [2405db86 ↗](https://jetty.io/jettyio/pelican-bicycle-svg/2405db86) | | v4 | 7self 10 | 7.7self 10 | 6.8self 9.5 | 7.2self 9.5 | 39 | 28.7 | 1.5 | – | [822a3bca ↗](https://jetty.io/jettyio/pelican-bicycle-svg/822a3bca) | | v5 | 7self 9.5 | 8.3self 9.5 | 7.2self 10 | 7.5self 9.8 | 38.8 | 30 | 0 | – | [60502506 ↗](https://jetty.io/jettyio/pelican-bicycle-svg/60502506) | | v6 | 6.3self 9.5 | 7.5self 9.5 | 6.3self 9.5 | 6.7self 9.5 | 38 | 26.8 | 0.5 | – | [2c2a74e8 ↗](https://jetty.io/jettyio/pelican-bicycle-svg/2c2a74e8) | | v7 | 5.8self 9.8 | 7.8self 9.5 | 6.7self 9.5 | 6.7self 9.7 | 38.5 | 27 | 2.5 | – | [c165de92 ↗](https://jetty.io/jettyio/pelican-bicycle-svg/c165de92) | | v8 | 5.5self 9 | 8self 10 | 6.2self 9 | 6.7self 10 | 38 | 26.3 | 1 | – | [d391e018 ↗](https://jetty.io/jettyio/pelican-bicycle-svg/d391e018) | | v9 | 6self 9.5 | 8self 10 | 6.8self 10 | 7.3self 10 | 39.5 | 28.2 | 2 | – | [e6d4548b ↗](https://jetty.io/jettyio/pelican-bicycle-svg/e6d4548b) | | v10 | 5.3self 9.8 | 8self 9.5 | 6.3self 9.5 | 6.8self 9.7 | 38.5 | 26.5 | 1 | – | [3e21bf05 ↗](https://jetty.io/jettyio/pelican-bicycle-svg/3e21bf05) | --- Source: https://evaljetty.com/pelicans/agents/hermes-flash.html · Evals by Jetty · Run your own evals: https://jetty.io/?utm_source=evaljetty&utm_medium=llms