Loading…
Ranked by total rewards from completed prompts.
| # | User | Total Won | Wins |
|---|---|---|---|
| 1 | 👤 | 17.84 USDC | 2 |
| 2 | 👤 | 13.1 USDC | 3 |
| 3 | 👤 | 6.82 USDC | 1 |
| 4 | 👤 | 1.74 USDC | 1 |
| 5 | 👤 | 0.57 USDC | 1 |
| 6 | 0.04 USDC | 1 |
Ranked by total user messages across prompts using each model.
| # | Model | User Messages | Prompts | Total Attempts |
|---|---|---|---|---|
| 1 | openai/chatgpt-4o-latest | 101 | 4 | 24 |
| 2 | anthropic/claude-opus-4 | 21 | 1 | 9 |
| 3 | anthropic/claude-opus-4.1 | 14 | 2 | 7 |
| 4 | openai/gpt-oss-120b | 12 | 1 | 6 |
| 5 | anthropic/claude-sonnet-4 | 9 | 1 | 2 |
| 6 | openai/gpt-5-chat | 8 | 4 | 6 |
| 7 | deepseek/deepseek-r1 | 6 | 1 | 7 |
| 8 | x-ai/grok-3-mini | 3 | 1 | 2 |
Ranked by the percentage of successful exploits.
| # | Model | Exploit % | Completions | User Messages |
|---|---|---|---|---|
| 1 | openai/gpt-5-chat | 37.50% | 3 | 8 |
| 2 | deepseek/deepseek-r1 | 16.67% | 1 | 6 |
| 3 | openai/chatgpt-4o-latest | 3.96% | 4 | 101 |
| 4 | anthropic/claude-opus-4 | 0.00% | 0 | 21 |
| 5 | anthropic/claude-opus-4.1 | 0.00% | 0 | 14 |
| 6 | openai/gpt-oss-120b | 0.00% | 0 | 12 |
| 7 | anthropic/claude-sonnet-4 | 0.00% | 0 | 9 |
| 8 | x-ai/grok-3-mini | 0.00% | 0 | 3 |