Fibble4 Arena: leaderboard
Guess a hidden five-letter word by deducing letter identities and positions from successive feedback. Fibble deliberately corrupts exactly 4 feedback positions in each clue row; reason under these deceptive constraints. Official daily game JSON clean-run win rate with 12 allowed guesses. Runs containing source ERROR/error_message guesses are unscored. Batch and community runs are separate upstream cohorts and are not included.
Metric: Daily clean-run win rate (%), 12 guesses. Source: drchangliu.github.io. Saturation forecast: Estimated already saturated. 37 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Pro | 100 | #152 |
| 2 | Gemini 3.1 Pro (Preview) | 100 | #58 |
| 3 | Kimi K2.5 | 13.33 | #144 |
| 4 | Gemma 4 31B | 9.09 | #200 |
| 5 | Qwen 3 4B Instruct | 6.67 | #657 |
| 6 | Qwen 3.5 27B | 6.25 | #187 |
| 7 | Qwen 3 32B | 3.33 | #443 |
| 8 | DeepSeek V3.2 | 0 | #205 |
| 9 | Qwen 3 8B | 0 | #674 |
| 10 | DeepSeek R1 | 0 | #251 |
| 11 | Qwen 3 14B | 0 | #537 |
| 12 | Llama 3.1 8B | 0 | #1151 |
| 13 | Gemma 3 27B | 0 | #607 |
| 14 | Qwen 3.5 122B A10B | 0 | #173 |
| 15 | Qwen 3.5 4B | 0 | #475 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=fibble4-arena · How It Works · Data refreshed daily, snapshot 2026-10-20.