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 · Writing & design

GameFeel Benchmark v1.5.1

The GameFeel Benchmark: each model adds 30 to 100 items, mechanics and balance changes of its own choosing to 12 unpublished game projects. Score: the board's Overall, the mean of its seven subcategories (creating, bug fixing, gamefeel, ideas, visuals, audio and reverse evaluation), out of 100. Gamefeel itself, how well the additions keep each game balanced, is rated 1 to 10 per task by human evaluators. All seven subcategory scores are kept in each row's details.

20 models · 26 results · updated 2026-11-16 · kodasdream.github.io ↗

Leaderboard

Fable 5.2 high

More from this benchmark

9 published measures

Breakdown

darker is better within each column · click a column to sort
Model
Fable 5.2 high69.067.051.042.064.030.045.5
Gemini 4 Carbon high64.056.051.047.067.033.040.248.0
Opus 5.5 max65.066.050.041.063.026.041.490.0
Gemini 4 Hydrogen high63.059.054.050.065.032.024.224.0
Sonnet 5.5 max65.065.048.039.054.021.010.890.0
DeepSeek V4.1 Flash 1017 max65.054.037.032.055.050.07.1185.0
Gemini 4 Argon high63.055.035.030.065.030.07.3635.0
MiMo V2.6 Pro max52.065.035.038.047.041.02.3180.0
Qwen 3.8 Flash xhigh55.055.050.042.027.040.0715.0
DeepSeek V4.1 Flash max62.057.045.034.035.043.01.8745.0
Qwen 3.8 Max xhigh56.040.047.041.030.042.06.8215.0
Haiku 5.5 max56.050.043.031.048.019.01.6822.0
Gemini 3.8 Flash max55.055.020.030.037.039.01.0275.0
Kimi K3.1 max63.055.010.010.045.027.07.3377.0
Ling 3.2 Flash max40.045.030.030.040.032.01.6548.0
GLM 5.3 Flash max57.062.032.025.018.022.00.396270.0
Qwen 3.7 Plus medium35.030.030.030.020.020.04.4115.0
Muse Spark 1.3 medium33.050.015.015.025.025.00.42990.0
MiniMax M3.1 max20.063.0010.030.030.00.473135.0
GPT-6 Luna xhigh50.015.0015.028.015.00.088496.0

All results

26 rows
#ModelEffortScore
1Fable 5.2high52.2
2Gemini 4 Carbonhigh50.4
3Opus 5.5max49.8
4Fable 5.2max48.2
5Gemini 4 Hydrogenhigh47.9
6Fable 5.2medium47.6
7Opus 5.5xhigh44.5
8Sonnet 5.5max41.1
9DeepSeek V4.1 Flash 1017max40.5
10Sonnet 5.5xhigh39.6
11Opus 5.5medium39.1
12Gemini 4 Argonhigh38.5
13MiMo V2.6 Promax37.5
14Qwen 3.8 Flashxhigh37.3
15DeepSeek V4.1 Flashmax37.2
16Sonnet 5.5medium36.0
17Qwen 3.8 Maxxhigh35.5
18Haiku 5.5max33.3
19Gemini 3.8 Flashmax31.7
20Kimi K3.1max29.5
21Ling 3.2 Flashmax29.3
22GLM 5.3 Flashmax28.9
23Qwen 3.7 Plusmedium22.9
24Muse Spark 1.3medium21.8
25MiniMax M3.1max20.5
26GPT-6 Lunaxhigh16.4