Support

Benchmarks · Writing & design

GameFeel Benchmark v1.5.2

Star0

The GameFeel Benchmark: each model adds 30 to 100 items, mechanics and balance changes of its own choosing to 12 unpublished game projects.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.

Quality 71 of 100 · Private test set · Has measured 6 of today's 10 default lineup models

23 models · 30 results · updated 2026-11-23 · kodasdream.github.io ↗

Leaderboard

Fable 5.2 max

Benchmark quality

How the score works
  • Overall
    71

    71 of 100

    How useful it is for telling today’s models apart

  • Headroom20%
    49

    Top models average 46 of 100

    Can top models still improve on it?

  • Test set20%
    100

    Private

    Could labs train on the questions?

  • Recency15%
    100

    3 days old

    How new is it?

  • Grading15%
    70

    Partly automatic

    How are answers scored?

  • New models15%
    60

    6 of 10 top models

    How fast does it test new releases?

  • Efforts10%
    35

    4 of 23 models at 2+ efforts

    Does it test each model at several reasoning efforts?

  • Breadth5%
    57

    23 models

    How many models has it measured?

How each part was worked out
Headroom 49 of 100 · 20% · +9.8
From the spread of published scores and the room left above the top quarter of models, one score per model.
Test set 100 of 100 · 20% · +20
Private test set. The 12 game projects are unpublished, so the scored content is hidden; only the CSV of scores is public. Source
Recency 100 of 100 · 15% · +15
Released 2026-11-19 (from the publisher's pages, not yet checked by hand).
Grading 70 of 100 · 15% · +10.5
Coding answers are checked against answer keys (Opus 5.5 only rules on formatting slips and near misses, never on quality); game feel, ideas, visuals and audio are rated by people.
New models 60 of 100 · 15% · +9
Has measured 6 of today's 10 default lineup models. Too few new models to time how quickly it adds them.
Efforts 35 of 100 · 10% · +3.5
Measured 4 of the 23 models that come in more than one reasoning effort at two or more of them.
Breadth 57 of 100 · 5% · +2.9
23 models measured.

Not counted in the score: 0 stars · used by 2 published pages. Both lift it in the directory’s recommended order. Test set, release date and grading were researched from the publisher’s pages (2026-11-19); tell us if one is wrong.

More from this benchmark

9 published measures

Breakdown

darker is better within each column · click a column to sort
Model
Fable 5.2 max71.069.051.042.064.031.018.0102.0
Gemini 4 Carbon high64.056.051.047.067.033.023.348.0
Gemini 4 Neon xhigh63.074.048.042.055.039.020.037.0
Gemini 4 Hydrogen high63.059.054.050.065.032.011.824.0
Opus 5.5 xhigh65.065.050.041.063.025.017.990.0
Gemini 4 Argon high63.055.035.030.065.030.025.435.0
ERNIE 5.5 Flash Preview max64.055.045.036.056.044.03.07
Sonnet 5.5 max65.065.048.039.054.021.08.2190.0
DeepSeek V4.1 Flash 1017 max65.054.037.032.055.050.05.3485.0
MiMo V2.6 Pro max52.065.035.038.047.041.01.9380.0
DeepSeek V4.1 Flash max62.057.045.034.035.043.01.5645.0
Qwen 3.8 Flash xhigh55.055.050.042.027.040.04.0315.0
Qwen 3.8 Max xhigh56.040.047.041.030.042.05.715.0
Haiku 5.5 max56.050.043.031.048.019.01.322.0
Gemini 3.8 Flash max55.055.020.030.037.039.00.85475.0
Ling 3.2 Flash max40.045.030.030.040.032.01.0848.0
GLM 5.3 Flash max57.062.032.025.018.022.00.331270.0
Kimi K3.1 max63.055.010.010.045.027.03.5377.0
Qwen 3.7 Plus medium35.030.030.030.020.020.03.6815.0
Muse Spark 1.3 medium33.050.015.015.025.025.00.35890.0
MiniMax M3.1 max20.063.0010.030.030.00.395135.0
GPT-6 Luna xhigh50.015.0015.028.015.00.025996.0
Nemotron 3.5 Super VL max9227.025.025.025.03.579

All results

30 rows
#ModelEffortScore
1Fable 5.2max47.3
2Gemini 4 Carbonhigh47.1
3Gemini 4 Neonxhigh46.8
4Fable 5.2medium46.7
5Fable 5.2high46.7
6Gemini 4 Hydrogenhigh45.4
7Opus 5.5xhigh44.8
8Opus 5.5max44.0
9Gemini 4 Neonmedium43.8
10Gemini 4 Argonhigh42.1
11ERNIE 5.5 Flash Previewmax40.6
12Sonnet 5.5max40.6
13DeepSeek V4.1 Flash 1017max40.1
14Sonnet 5.5xhigh39.3
15Opus 5.5medium38.9
16MiMo V2.6 Promax37.5
17DeepSeek V4.1 Flashmax37.1
18Qwen 3.8 Flashxhigh36.7
19Sonnet 5.5medium35.8
20Qwen 3.8 Maxxhigh35.3
21Haiku 5.5max33.2
22Gemini 3.8 Flashmax31.6
23Ling 3.2 Flashmax29.1
24GLM 5.3 Flashmax28.9
25Kimi K3.1max28.7
26Qwen 3.7 Plusmedium22.7
27Muse Spark 1.3medium21.8
28MiniMax M3.1max20.5
29GPT-6 Lunaxhigh16.4
30Nemotron 3.5 Super VLmax15.8