Wordle Arena: leaderboard
Guess a hidden five-letter word by deducing letter identities and positions from successive feedback. Standard truthful Wordle feedback. Official daily game JSON clean-run win rate with 6 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 (%), 6 guesses. Source: drchangliu.github.io. Saturation forecast: Estimated already saturated. 47 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Pro | 100 | #152 |
| 2 | Claude Opus 4.6 | 100 | #63 |
| 3 | GPT-5 Mini | 100 | #186 |
| 4 | Claude Sonnet 4 | 100 | #199 |
| 5 | Qwen 3.5 27B | 100 | #187 |
| 6 | Qwen 3.5 122B A10B | 100 | #173 |
| 7 | Qwen 3.5 4B | 100 | #475 |
| 8 | Gemma 4 31B | 100 | #200 |
| 9 | QwQ-32B | 100 | #421 |
| 10 | Claude Opus 4 | 100 | #163 |
| 11 | Gemma 4 26B | 100 | #292 |
| 12 | Gemini 3.1 Pro (Preview) | 97.22 | #58 |
| 13 | Qwen 3 30B A3B | 96.67 | #493 |
| 14 | Kimi K2.5 | 95.24 | #144 |
| 15 | GPT-5 | 76.92 | #98 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=wordle-arena · How It Works · Data refreshed daily, snapshot 2026-10-20.