{ "qwen2.5-3b-instruct": { "success_rate": 0.0624, "relative_action_count": 2.4255102697302697 }, "llama-3.2-3b-instruct": { "success_rate": 0.064, "relative_action_count": 2.4438042524142523 }, "llama-3.1-8b-instruct": { "success_rate": 0.11599999999999999, "relative_action_count": 2.3321907026307027 }, "gpt-3.5-turbo": { "success_rate": 0.12079999999999999, "relative_action_count": 2.34957508047508 }, "gemma-2-9b-it": { "success_rate": 0.132, "relative_action_count": 2.3394684981684977 }, "qwen2.5-7b-instruct": { "success_rate": 0.1664, "relative_action_count": 2.3259762459762454 }, "gemma-2-27b-it": { "success_rate": 0.1696, "relative_action_count": 2.28467764013764 }, "llama-3.1-70b-instruct": { "success_rate": 0.256, "relative_action_count": 1.9653564912864916 }, "yi-lightning": { "success_rate": 0.30720000000000003, "relative_action_count": 2.031278719058719 }, "gpt-4o-mini": { "success_rate": 0.31040000000000006, "relative_action_count": 1.9804984304584305 }, "llama-3.3-70b-instruct": { "success_rate": 0.33840000000000003, "relative_action_count": 1.90917626040626 }, "claude-3.5-haiku": { "success_rate": 0.3592000000000001, "relative_action_count": 2.0113219180819177 }, "gemini-1.5-pro": { "success_rate": 0.36879999999999996, "relative_action_count": 1.9371788544788544 }, "qwen2.5-14b-instruct": { "success_rate": 0.3816, "relative_action_count": 1.9383408547008547 }, "qwen2.5-72b-instruct": { "success_rate": 0.4008, "relative_action_count": 1.8648658674658674 }, "mistral-large-instruct-2411": { "success_rate": 0.4144, "relative_action_count": 1.795764299034299 }, "qwen2.5-32b-instruct": { "success_rate": 0.43920000000000003, "relative_action_count": 1.8831460717060717 }, "claude-3.5-sonnet": { "success_rate": 0.44000000000000006, "relative_action_count": 1.6636790032190032 }, "gpt-4o": { "success_rate": 0.44960000000000006, "relative_action_count": 1.7164597657897656 }, "deepseek-v3": { "success_rate": 0.5496000000000001, "relative_action_count": 1.705338828948829 }, "deepseek-r1": { "success_rate": 0.6112, "relative_action_count": 1.4205231568431569 }, "qwq-32b": { "success_rate": 0.6112, "relative_action_count": 1.5151790675990677 }, "o1-mini": { "success_rate": 0.6296, "relative_action_count": 1.4230264535464534 } }