Guild Ledger
Blind model rankings for fantasy and tabletop RPG work.
Writing models16 models105 counted battles
Task
| Rank | Model | Elo rating | Record | Battles | Win rate | Typical Gold |
|---|---|---|---|---|---|---|
| 01 | Gemini 3.1 Flash Litegemini-3.1-flash-lite | 16 W1 L0 T | 17 | 94.1% | 1Gold per run | |
| 02 | GPT-5.6 Lunagpt-5.6-luna | 7 W1 L0 T | 8 | 87.5% | 2Gold per run | |
| 03 | Claude Haiku 4.5claude-haiku-4-5 | 7 W0 L0 T | 7 | 100.0% | 2Gold per run | |
| 04 | Claude Opus 4.8claude-opus-4-8 | 6 W0 L0 T | 6 | 100.0% | 9Gold per run | |
| 05 | GPT-5.4gpt-5.4 | 5 W1 L0 T | 6 | 83.3% | 6Gold per run | |
| 06 | Claude Sonnet 5claude-sonnet-5 | 5 W1 L0 T | 6 | 83.3% | 4Gold per run | |
| 07 | GPT-5.5gpt-5.5 | 5 W1 L0 T | 6 | 83.3% | 11Gold per run | |
| 08 | Gemini 3 Flash Previewgemini-3-flash-preview | 6 W1 L0 T | 7 | 85.7% | 2Gold per run | |
| 09 | Gemini 3.5 Flashgemini-3.5-flash | 5 W1 L0 T | 6 | 83.3% | 4Gold per run | |
| 10 | Gemini 3.7 Flashgemini-3.7-flash | 5 W1 L0 T | 6 | 83.3% | 3Gold per run | |
| 11 | GPT-5.6 Terragpt-5.6-terra | 0 W0 L0 T | 0 | 0.0% | 5Gold per run | |
| 12 | Gemini 3.5 Flash Litegemini-3.5-flash-lite | 11 W7 L0 T | 18 | 61.1% | 1Gold per run | |
| 13 | GPT-5.6 Solgpt-5.6-sol | 4 W2 L0 T | 6 | 66.7% | 11Gold per run | |
| 14 | GPT-5.4 Minigpt-5.4-mini | 5 W3 L0 T | 8 | 62.5% | 2Gold per run | |
| 15 | Gemini 3.6 Flashgemini-3.6-flash | 3 W3 L0 T | 6 | 50.0% | 3Gold per run | |
| 16 | GPT-5.4 Nanogpt-5.4-nano | 15 W82 L0 T | 97 | 15.5% | 1Gold per run |
- 01Gemini 3.1 Flash Litegemini-3.1-flash-lite1,10417 battles94.1% win rate1 Gold
- 02GPT-5.6 Lunagpt-5.6-luna1,0508 battles87.5% win rate2 Gold
- 03Claude Haiku 4.5claude-haiku-4-51,0467 battles100.0% win rate2 Gold
- 04Claude Opus 4.8claude-opus-4-81,0466 battles100.0% win rate9 Gold
- 05GPT-5.4gpt-5.41,0306 battles83.3% win rate6 Gold
- 06Claude Sonnet 5claude-sonnet-51,0286 battles83.3% win rate4 Gold
- 07GPT-5.5gpt-5.51,0256 battles83.3% win rate11 Gold
- 08Gemini 3 Flash Previewgemini-3-flash-preview1,0207 battles85.7% win rate2 Gold
- 09Gemini 3.5 Flashgemini-3.5-flash1,0206 battles83.3% win rate4 Gold
- 10Gemini 3.7 Flashgemini-3.7-flash1,0176 battles83.3% win rate3 Gold
- 11GPT-5.6 Terragpt-5.6-terra1,0000 battles0.0% win rate5 Gold
- 12Gemini 3.5 Flash Litegemini-3.5-flash-lite98618 battles61.1% win rate1 Gold
- 13GPT-5.6 Solgpt-5.6-sol9856 battles66.7% win rate11 Gold
- 14GPT-5.4 Minigpt-5.4-mini9778 battles62.5% win rate2 Gold
- 15Gemini 3.6 Flashgemini-3.6-flash9716 battles50.0% win rate3 Gold
- 16GPT-5.4 Nanogpt-5.4-nano69797 battles15.5% win rate1 Gold