Benchmarks · creative
GameFeel Benchmark
The GameFeel Benchmark: each model adds 30 to 100 items, mechanics and balance changes of its own choosing to 12 unpublished game projects.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.
19 models · 23 results · updated 2026-11-09 · kodasdream.github.io ↗
Leaderboard
Gemini 4 Carbon high
More from this benchmark
9 published measuresScore vs any published measure9 measures: sub-scores, splits, counts
11 more models under All models in settings.
Breakdown
darker is better within each column · click a column to sort| Model | ||||||||
|---|---|---|---|---|---|---|---|---|
| Gemini 4 Carbon high | 64.0 | 56.0 | 51.0 | 47.0 | 67.0 | 33.0 | 84.2 | 48.0 |
| Fable 5.2 max | 71.0 | 69.0 | 51.0 | 42.0 | 64.0 | 31.0 | 48.7 | 102.0 |
| Opus 5.5 xhigh | 65.0 | 65.0 | 50.0 | 41.0 | 63.0 | 25.0 | 21.7 | 90.0 |
| Sonnet 5.5 max | 65.0 | 65.0 | 48.0 | 39.0 | 54.0 | 21.0 | 23.3 | 90.0 |
| DeepSeek V4.1 Flash 1017 max | 65.0 | 54.0 | 37.0 | 32.0 | 55.0 | 50.0 | 6.53 | 85.0 |
| Gemini 4 Argon high | 63.0 | 55.0 | 35.0 | 30.0 | 65.0 | 30.0 | 13.2 | 35.0 |
| MiMo V2.6 Pro max | 52.0 | 65.0 | 35.0 | 38.0 | 47.0 | 41.0 | 4.47 | 80.0 |
| Qwen 3.8 Flash xhigh | 55.0 | 55.0 | 50.0 | 42.0 | 27.0 | 40.0 | 13.0 | 15.0 |
| DeepSeek V4.1 Flash max | 62.0 | 57.0 | 45.0 | 34.0 | 35.0 | 43.0 | 5.51 | 45.0 |
| Qwen 3.8 Max xhigh | 56.0 | 40.0 | 47.0 | 41.0 | 30.0 | 42.0 | 12.1 | 15.0 |
| Haiku 5.5 xhigh | 56.0 | 50.0 | 43.0 | 31.0 | 48.0 | 19.0 | 5.6 | 22.0 |
| Gemini 3.8 Flash max | 55.0 | 55.0 | 20.0 | 30.0 | 37.0 | 39.0 | 1.82 | 75.0 |
| Ling 3.2 Flash max | 40.0 | 45.0 | 30.0 | 30.0 | 40.0 | 32.0 | 3.81 | 48.0 |
| GLM 5.3 Flash max | 57.0 | 62.0 | 32.0 | 25.0 | 18.0 | 22.0 | 0.63 | 270.0 |
| Kimi K3.1 max | 63.0 | 55.0 | 10.0 | 10.0 | 45.0 | 27.0 | 0.12 | 77.0 |
| Qwen 3.7 Plus medium | 35.0 | 30.0 | 30.0 | 30.0 | 20.0 | 20.0 | 7.4 | 15.0 |
| Muse Spark 1.3 medium | 33.0 | 50.0 | 15.0 | 15.0 | 25.0 | 25.0 | 0.7 | 90.0 |
| MiniMax M3.1 max | 20.0 | 63.0 | 0 | 10.0 | 30.0 | 30.0 | 0.9 | 135.0 |
| GPT-6 Luna max | 50.0 | 15.0 | 0 | 15.0 | 28.0 | 15.0 | 0.06 | 96.0 |
All results
23 rows| # | Model | Effort | GameFeel Benchmark |
|---|---|---|---|
| 1 | Gemini 4 Carbon | high | 57.5 |
| 2 | Fable 5.2 | max | 53.8 |
| 3 | Fable 5.2 | medium | 53.7 |
| 4 | Opus 5.5 | xhigh | 47.2 |
| 5 | Sonnet 5.5 | max | 45.0 |
| 6 | Sonnet 5.5 | xhigh | 42.8 |
| 7 | DeepSeek V4.1 Flash 1017 | max | 42.8 |
| 8 | Opus 5.5 | medium | 42.3 |
| 9 | Gemini 4 Argon | high | 41.6 |
| 10 | MiMo V2.6 Pro | max | 40.4 |
| 11 | Qwen 3.8 Flash | xhigh | 40.3 |
| 12 | DeepSeek V4.1 Flash | max | 40.2 |
| 13 | Sonnet 5.5 | medium | 38.8 |
| 14 | Qwen 3.8 Max | xhigh | 38.3 |
| 15 | Haiku 5.5 | xhigh | 36.1 |
| 16 | Gemini 3.8 Flash | max | 34.0 |
| 17 | Ling 3.2 Flash | max | 31.5 |
| 18 | GLM 5.3 Flash | max | 30.9 |
| 19 | Kimi K3.1 | max | 30.0 |
| 20 | Qwen 3.7 Plus | medium | 24.6 |
| 21 | Muse Spark 1.3 | medium | 23.4 |
| 22 | MiniMax M3.1 | max | 22.0 |
| 23 | GPT-6 Luna | max | 17.6 |