MCPcopy Create free account

hub / github.com/disler/benchy / functions

Functions126 in github.com/disler/benchy

Functiontest_partial_xml_handling
()
server/tests/utils_test.py:16
Functiontest_phi_4_text_prompt
()
server/tests/ollama_llm_test.py:26
Functiontest_predictive_prompt
()
server/tests/llm_modules_test.py:7
Functiontest_predictive_prompt_autocomplete
(input_text, expected_completion)
server/tests/llm_modules_test.py:38
Functiontest_prompt
(client, model)
server/tests/server_test.py:28
Functiontest_prompt_ping
(model_alias)
server/tests/llm_modules_test.py:89
Functiontest_qwen_text_prompt
()
server/tests/ollama_llm_test.py:12
Functiontest_run_coder_agent
()
server/tests/tools_test.py:4
Functiontest_run_docs_agent
()
server/tests/tools_test.py:16
Functiontest_run_git_agent
()
server/tests/tools_test.py:10
Functiontest_text_prompt
(model)
server/tests/fireworks_llm_test.py:18
Functiontest_text_prompt_reasoning_effort
Test that text_prompt works with real API calls and that our parsing works.
server/tests/openai_llm_test.py:87
Functiontest_think_tag_parsing
()
server/tests/utils_test.py:1
Functiontest_thought_bench_deepseek
Test thought bench endpoint with DeepSeek Reasoner model
server/tests/server_test.py:109
Functiontest_thought_bench_ollama
Test thought bench endpoint with Ollama DeepSeek model
server/tests/server_test.py:89
Functiontest_thought_prompt
()
server/tests/fireworks_llm_test.py:26
Functiontest_thought_prompt_happy_path
()
server/tests/deepseek_llm_test.py:38
Functiontest_thought_prompt_missing_thoughts
()
server/tests/deepseek_llm_test.py:51
Functiontest_tool_prompt
( prompt: str, expected_tool_calls: list[SimpleToolCall], model: str )
server/tests/openai_llm_test.py:36
Functiontest_tool_prompt
(client, prompt, expected_tool_calls, model)
server/tests/server_test.py:51
Functiontest_valid_xml_parsing
()
server/tests/ollama_llm_test.py:63
Functionthought_prompt
Handle thought prompt requests with specialized parsing for supported models. Fall back to standard text prompts for other models.
server/modules/llm_models.py:75
Functionthought_prompt
Handle thought prompts for DeepSeek R1 models running on Ollama.
server/modules/ollama_llm.py:43
Functiontool_prompt
Run a chat model with tool calls using Anthropic's Claude. Now supports JSON structured output variants by parsing the response.
server/modules/anthropic_llm.py:118
Functiontool_prompt
(prompt: PromptWithToolCalls)
server/modules/llm_models.py:53
Functiontool_prompt
Run a chat model with tool calls using Gemini's API. Now supports JSON structured output variants by parsing the response.
server/modules/gemini_llm.py:159
← previous101–126 of 126, ranked by callers