--- title: "claude-code \u00b7 Sonnet 4.6 | Pelican benchmark" url: https://evaljetty.com/pelicans/agents/claude-sonnet.html description: "claude-code \u00b7 Sonnet 4.6 (claude-sonnet-4-6) 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 · hand-curated runbook edits # claude-code · Sonnet 4.6 The reference lineage: Jon edited the runbook by hand eleven times, reading each trajectory before writing the next version. agent **claude-code** · model **claude-sonnet-4-6** Judge, best round 26.2/40 round v5 Self-score, best round 37/40 inflation +10.8 Rounds 11 Jetty trajectories ![claude-code · Sonnet 4.6 best round](https://evaljetty.com/pelicans/img/claude-sonnet/v5.svg) best round v5 · [7ddc3c19 ↗](https://jetty.io/jettyio/pelican-bicycle-svg/7ddc3c19) ### Self-score vs judge, by axis Best round v5, 0–10 per axis agent self-scoreexternal judge **Judge:** The pelican reads as a pelican thanks to the large orange pouch and white body. The beak is a boxy block, the head has odd buck-teeth-like shapes, and the wings are messy. The bicycle has spoked wheels, a plausible frame, a handlebar and a crank, but the seat is hidden and the fork and frame geometry are slightly off. The pelican sits on the frame with long legs reaching the pedals and a wing gripping the handlebar, which sells the riding pose. Clean colors and background, though the head and pouch shapes are crude. ### 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. [![claude-code · Sonnet 4.6 round v1](https://evaljetty.com/pelicans/img/claude-sonnet/v1.svg)](https://evaljetty.com/pelicans/head-to-head.html#claude-sonnet/v1) **v1**judge **26.5** · self 31 [7ddfcf08 ↗](https://jetty.io/jettyio/pelican-bicycle-svg/7ddfcf08)[runbook](https://evaljetty.com/pelicans/runbooks.html#claude-sonnet/v1) [![claude-code · Sonnet 4.6 round v2](https://evaljetty.com/pelicans/img/claude-sonnet/v2.svg)](https://evaljetty.com/pelicans/head-to-head.html#claude-sonnet/v2) **v2**judge **25.2** · self 32 [414e644d ↗](https://jetty.io/jettyio/pelican-bicycle-svg/414e644d)[runbook](https://evaljetty.com/pelicans/runbooks.html#claude-sonnet/v2) [![claude-code · Sonnet 4.6 round v3](https://evaljetty.com/pelicans/img/claude-sonnet/v3.svg)](https://evaljetty.com/pelicans/head-to-head.html#claude-sonnet/v3) **v3**judge **24.5** · self 34 [b169371d ↗](https://jetty.io/jettyio/pelican-bicycle-svg/b169371d)[runbook](https://evaljetty.com/pelicans/runbooks.html#claude-sonnet/v3) [![claude-code · Sonnet 4.6 round v4](https://evaljetty.com/pelicans/img/claude-sonnet/v4.svg)](https://evaljetty.com/pelicans/head-to-head.html#claude-sonnet/v4) **v4**judge **24.5** · self 36 [063dfed9 ↗](https://jetty.io/jettyio/pelican-bicycle-svg/063dfed9)[runbook](https://evaljetty.com/pelicans/runbooks.html#claude-sonnet/v4) [![claude-code · Sonnet 4.6 round v5](https://evaljetty.com/pelicans/img/claude-sonnet/v5.svg)](https://evaljetty.com/pelicans/head-to-head.html#claude-sonnet/v5) **v5** · bestjudge **26.2** · self 37 [7ddc3c19 ↗](https://jetty.io/jettyio/pelican-bicycle-svg/7ddc3c19)[runbook](https://evaljetty.com/pelicans/runbooks.html#claude-sonnet/v5) [![claude-code · Sonnet 4.6 round v6](https://evaljetty.com/pelicans/img/claude-sonnet/v6.svg)](https://evaljetty.com/pelicans/head-to-head.html#claude-sonnet/v6) **v6**judge **26.5** · self 36 [39febb11 ↗](https://jetty.io/jettyio/pelican-bicycle-svg/39febb11)[runbook](https://evaljetty.com/pelicans/runbooks.html#claude-sonnet/v6) [![claude-code · Sonnet 4.6 round v7](https://evaljetty.com/pelicans/img/claude-sonnet/v7.svg)](https://evaljetty.com/pelicans/head-to-head.html#claude-sonnet/v7) **v7**judge **27.7** · self 34 [ddf779bd ↗](https://jetty.io/jettyio/pelican-bicycle-svg/ddf779bd)[runbook](https://evaljetty.com/pelicans/runbooks.html#claude-sonnet/v7) [![claude-code · Sonnet 4.6 round v8](https://evaljetty.com/pelicans/img/claude-sonnet/v8.svg)](https://evaljetty.com/pelicans/head-to-head.html#claude-sonnet/v8) **v8**judge **26.3** · self 34 [79fdee62 ↗](https://jetty.io/jettyio/pelican-bicycle-svg/79fdee62)[runbook](https://evaljetty.com/pelicans/runbooks.html#claude-sonnet/v8) [![claude-code · Sonnet 4.6 round v9](https://evaljetty.com/pelicans/img/claude-sonnet/v9.svg)](https://evaljetty.com/pelicans/head-to-head.html#claude-sonnet/v9) **v9**judge **25.8** · self 33 [5f980543 ↗](https://jetty.io/jettyio/pelican-bicycle-svg/5f980543)[runbook](https://evaljetty.com/pelicans/runbooks.html#claude-sonnet/v9) [![claude-code · Sonnet 4.6 round v10](https://evaljetty.com/pelicans/img/claude-sonnet/v10.svg)](https://evaljetty.com/pelicans/head-to-head.html#claude-sonnet/v10) **v10**judge **28** · self 35 [2043d7e3 ↗](https://jetty.io/jettyio/pelican-bicycle-svg/2043d7e3)[runbook](https://evaljetty.com/pelicans/runbooks.html#claude-sonnet/v10) [![claude-code · Sonnet 4.6 round v11](https://evaljetty.com/pelicans/img/claude-sonnet/v11.svg)](https://evaljetty.com/pelicans/head-to-head.html#claude-sonnet/v11) **v11**judge **25.3** · self 35 [3a4c3357 ↗](https://jetty.io/jettyio/pelican-bicycle-svg/3a4c3357)[runbook](https://evaljetty.com/pelicans/runbooks.html#claude-sonnet/v11) ### Scores per round | Round | Pelican | Bicycle | Composition | Polish | Self total | Judge total | Judge spread | Minutes | Trajectory | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | v1 | 6.7self 8 | 6.5self 8 | 6.7self 7 | 6.7self 8 | 31 | 26.5 | 1 | 7 | [7ddfcf08 ↗](https://jetty.io/jettyio/pelican-bicycle-svg/7ddfcf08) | | v2 | 5.7self 8 | 6.7self 8 | 6.7self 8 | 6.2self 8 | 32 | 25.2 | 1 | 12.6 | [414e644d ↗](https://jetty.io/jettyio/pelican-bicycle-svg/414e644d) | | v3 | 5.7self 9 | 6.2self 9 | 6.7self 8 | 6self 8 | 34 | 24.5 | 1.5 | 10.3 | [b169371d ↗](https://jetty.io/jettyio/pelican-bicycle-svg/b169371d) | | v4 | 5.3self 9 | 6.7self 9 | 6.7self 9 | 5.8self 9 | 36 | 24.5 | 2.5 | 7 | [063dfed9 ↗](https://jetty.io/jettyio/pelican-bicycle-svg/063dfed9) | | v5 | 5.8self 9 | 7self 9 | 7self 10 | 6.3self 9 | 37 | 26.2 | 1 | 7.8 | [7ddc3c19 ↗](https://jetty.io/jettyio/pelican-bicycle-svg/7ddc3c19) | | v6 | 6.2self 9 | 6.8self 9 | 7self 9 | 6.5self 9 | 36 | 26.5 | 3 | 5.4 | [39febb11 ↗](https://jetty.io/jettyio/pelican-bicycle-svg/39febb11) | | v7 | 6.8self 8 | 6.8self 9 | 7.5self 9 | 6.5self 8 | 34 | 27.7 | 0.5 | 13.8 | [ddf779bd ↗](https://jetty.io/jettyio/pelican-bicycle-svg/ddf779bd) | | v8 | 6self 8 | 6.8self 9 | 7self 8 | 6.5self 9 | 34 | 26.3 | 3.5 | 5.3 | [79fdee62 ↗](https://jetty.io/jettyio/pelican-bicycle-svg/79fdee62) | | v9 | 6self 8 | 6.7self 9 | 6.7self 7 | 6.5self 9 | 33 | 25.8 | 1 | 7.3 | [5f980543 ↗](https://jetty.io/jettyio/pelican-bicycle-svg/5f980543) | | v10 | 6.8self 9 | 7.2self 9 | 7.2self 8 | 6.8self 9 | 35 | 28 | 1.5 | 6.7 | [2043d7e3 ↗](https://jetty.io/jettyio/pelican-bicycle-svg/2043d7e3) | | v11 | 6self 9 | 6.7self 9 | 6.3self 8 | 6.3self 9 | 35 | 25.3 | 1 | 9.5 | [3a4c3357 ↗](https://jetty.io/jettyio/pelican-bicycle-svg/3a4c3357) | --- Source: https://evaljetty.com/pelicans/agents/claude-sonnet.html · Evals by Jetty · Run your own evals: https://jetty.io/?utm_source=evaljetty&utm_medium=llms