Support

Settings

Theme

Explore themes

Mode

Library

Looks borrowed from benchmark sites and products. Themes with a light and a dark version follow your mode.

Bring your own theme

Upload a Priors theme file, or have your agent make one: copy the prompt, tell it the look you want, and upload what it returns. With the Priors skill installed it already knows the format.

Custom themes stay in this browser. They travel inside shared chart links and a page's theme, so others see them as you do.

For the builder, Explore and model pages on this device. Published pages keep the theme their owner picked.

Mode

Update notices

A note when a benchmark one of your indexes uses gets a new version, with a one-click upgrade.

Benchmarks · Games & strategy · Agents & computer use

OpenTTD-Bench

Running a transport company in OpenTTD, a Transport Tycoon remake, for three in-game years on one fixed map, through game tools while the clock keeps running. Median final-year operating profit in pounds over at least five verified games. By Dylan Fetch.

11 models · 12 results · data as of 2026-11-13 · openttd-bench.com ↗

Leaderboard

Opus 5.5 xhigh

Score vs subscription cost per task

Highlight models

Click a point on the chart to highlight that exact effort; click it again to remove it.

Heavy line: best score at each price. Thin lines join one model's effort levels. Cost uses each model's median subscription plan, or API price with no plan data. 2 more models under All models in settings.

More from this benchmark

7 published measures

Breakdown

darker is better within each column · click a column to sort
Model
Opus 5.5 xhigh5855,343124.03,19519,17982.9512.0
GPT-6 Astra high5739,451101.03,37320,56582.4449.0
Grok 4.7 xhigh5479,51565.03,21915,33380.0405.0
Fable 5.1 high5459,82686.02,22714,08076.2375.0
GPT-6 Sol xhigh5357,14878.02,35911,24376.9546.0
Grok 4.6 xhigh5323,68880.01,90817,39574.2475.0
Opus 5 xhigh10.0391,76175.02,47716,85177.1305.5
DeepSeek V4.1 Flash max5198,82851.02,0834,89072.7381.0
GPT-5.6 Sol xhigh5123,56660.01,7215,84666.8334.0
DeepSeek V4 Flash max10.0139,65236.52,1084,65075.5317.0
MiMo V2.6 Pro high545,11910.02,0402,22066.491.0

All results

12 rows
#ModelEffortOpenTTD-BenchSubscription $ / taskAPI $ / taskHarness
1Opus 5.5xhigh415300.0$0.19$13Claude Code
2Opus 5.5max373178.0$0.19$13Claude Code
3GPT-6 Astrahigh336371.0$0.50$12Codex
4Grok 4.7xhigh239886.0Cursor Agent
5Fable 5.1high191552.0$1.85$12Claude Code
6GPT-6 Solxhigh182008.0Codex
7Grok 4.6xhigh167880.0Cursor Agent
8Opus 5xhigh156455.0$0.20$12Claude Code
9DeepSeek V4.1 Flashmax106245.0$0.020$0.27Pi
10GPT-5.6 Solxhigh85594.0Codex
11DeepSeek V4 Flashmax73762.0$0.013$0.25Pi
12MiMo V2.6 Prohigh26526.0$0.12$0.15Pi