Benchmarks · Writing & design
GameFeel Reverse Evaluation v1.5.2
Star1GameFeel's reverse evaluation (RE), made much harder in v1.5: how well the model gives feedback on game proposals, especially on balance. Score: the board's RE (combined), about two thirds blind runs and one third assisted runs, where the model first sees 39 worked examples; out of 100. Blind and assisted scores are kept in each row's details.
Quality 84 of 100 · Private test set · Has measured 9 of today's 10 default lineup models
35 models · 52 results · updated 2026-11-23 · kodasdream.github.io ↗
Leaderboard
Benchmark quality
How the score works- Overall84
84 of 100
How useful it is for telling today’s models apart
- Headroom20%68
Top models average 18 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%85
Checked automatically
How are answers scored?
- New models15%90
9 of 10 top models
How fast does it test new releases?
- Efforts10%51
9 of 35 models at 2+ efforts
Does it test each model at several reasoning efforts?
- Breadth5%88
35 models
How many models has it measured?
How each part was worked out
- Headroom 68 of 100 · 20% · +13.6
- 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 The reverse-evaluation items and answer keys are unpublished: over 8,000 tasks from the unpublished games (748 in a semi-private subset), plus a released-games part rating changes to commercial games such as Balatro, weighted 2 of 13. Source
- Recency 100 of 100 · 15% · +15
- Released 2026-11-19 (from the publisher's pages, not yet checked by hand).
- Grading 85 of 100 · 15% · +12.8
- Each rating is scored against a ground-truth answer key by a formula (rating error, ranking and separation); no model judges.
- New models 90 of 100 · 15% · +13.5
- Has measured 9 of today's 10 default lineup models. Too few new models to time how quickly it adds them.
- Efforts 51 of 100 · 10% · +5.1
- Measured 9 of the 35 models that come in more than one reasoning effort at two or more of them.
- Breadth 88 of 100 · 5% · +4.4
- 35 models measured.
Not counted in the score: 1 star · 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
2 published measuresScore vs any published measure
2 more models under All models in settings.
Breakdown
darker is better within each column · click a column to sort| Model | ||
|---|---|---|
| Gemini 4 Neon medium | 22.7 | 38.5 |
| Gemini 4 Argon high | 24.4 | 33.8 |
| Gemini 4 Carbon high | 19.8 | 30.5 |
| Opus 5.5 xhigh | 19.8 | 24.1 |
| GPT-6.2 Astra high | 8.32 | 26.1 |
| Gemini 4 Hydrogen xhigh | 10.5 | 14.3 |
| GPT-6.2 Sol medium | 4.08 | 12.3 |
| Haiku 5.5 xhigh | 6.49 | 8.48 |
| DeepSeek V4.1 Flash 1017 max | 4.75 | 3.3 |
| Inkling 2 Small max | 0.76 | 1.12 |
All results
52 rows| # | Model | Effort | Score |
|---|---|---|---|
| 1 | Gemini 4 Neon | medium | 25.4 |
| 2 | Gemini 4 Argon | high | 25.4 |
| 3 | Gemini 4 Carbon | high | 23.3 |
| 4 | Fable 5.2 | medium | 20.9 |
| 5 | Gemini 4 Neon | xhigh | 20.0 |
| 6 | Gemini 4 Carbon | medium | 18.0 |
| 7 | Fable 5.2 | max | 18.0 |
| 8 | Fable 5.2 | high | 17.9 |
| 9 | Opus 5.5 | xhigh | 17.9 |
| 10 | GPT-6.2 Astra | high | 14.6 |
| 11 | GPT-6.2 Astra | max | 14.4 |
| 12 | Gemini 4 Hydrogen | xhigh | 13.6 |
| 13 | Opus 5.5 | max | 12.5 |
| 14 | Gemini 4 Hydrogen | high | 11.8 |
| 15 | Gemini 4 Carbon | low | 10.6 |
| 16 | Gemini 4 Hydrogen | medium | 10.5 |
| 17 | GPT-6.2 Sol | medium | 8.7 |
| 18 | Sonnet 5.5 | max | 8.2 |
| 19 | Opus 5.5 | medium | 7.0 |
| 20 | Sonnet 5.5 | xhigh | 6.5 |
| 21 | Qwen 4 Max | xhigh | 6.2 |
| 22 | Haiku 5.5 | xhigh | 6.0 |
| 23 | Qwen 3.8 Max | xhigh | 5.7 |
| 24 | DeepSeek V4.1 Flash 1017 | max | 5.3 |
| 25 | Haiku 5.5 | high | 5.1 |
| 26 | Sonnet 5.5 | medium | 4.3 |
| 27 | Qwen 3.8 Flash | xhigh | 4.0 |
| 28 | GPT-6.2 Sol | high | 3.8 |
| 29 | Qwen 3.7 Plus | medium | 3.7 |
| 30 | Nemotron 3.5 Super VL | max | 3.6 |