Update readme

README.md

@@ -107,7 +107,7 @@ When specifying just the `--model` argument, the following configurations are us
 | gpt-4o-2024-11-20 | tool_call | messages | yes | [32%](https://experiments.moatless.ai/evaluations/20250119_azure_gpt_4o_0_0_n_20_fmt_tool_call_thoughts-in-action_1_verified_mini) |
 | gpt-4o-mini-2024-07-18 | tool_call | messages | yes | [16%](https://experiments.moatless.ai/evaluations/20250118_gpt_4o_mini_2024_07_18_0_0_n_20_fmt_tool_call_thoughts-in-action_6_verified_mini) |
 | o1-mini-2024-09-12 | react | react | no (disabled thoughts) | [28%](https://experiments.moatless.ai/evaluations/20250114_o1_mini_2024_09_12_0_0_n_20_fmt_react_hist_react_verified_mini) |
-| deepseek/deepseek-chat | react | react | yes | [36%](https://experiments.moatless.ai/evaluations/20250118_deepseek_deepseek_chat_0_0_n_20_fmt_react_verified_mini) |
+| deepseek/deepseek-chat | react | react | no | [36%](https://experiments.moatless.ai/evaluations/20250118_deepseek_deepseek_chat_0_0_n_20_fmt_react_verified_mini) |
 | gemini/gemini-2.0-flash-exp | react | react | no | [38%](https://experiments.moatless.ai/evaluations/20250119_gemini_gemini_2.0_flash_exp_0_0_n_20_fmt_react_verified_mini) |
 | openrouter/meta-llama/llama-3.1-70b-instruct | react | react | no | - |
 | openrouter/meta-llama/llama-3.1-405b-instruct | react | react | no | [28%](https://experiments.moatless.ai/evaluations/20250119_openai_meta_llama_Meta_Llama_3.1_405B_Instruct_FP8_0_0_n_20_fmt_react_verified_mini) | - |