gorilla · Issues· 280 open

[BFCL] Several multi_turn_base items have ground truth that cannot be produced from the environment

[BFCL] Eager import of qwen_agent forces audio deps on Claude-only users

Irrelevance detection credits a tool call that failed to parse as a correct abstention

Would an EvalPort-format export of BFCL be welcome in EvalPort's benchmarks/?

[BFCL] DeepSeek v4?

[BFCL] Clarify default and ablation behavior of synthetic request failures in BFCL V4 Web Search

[BFCL] Strict regex-based evaluator gives false negatives even on semantically accurate model responses

[BFCL] simple_python_363: release-commit answer key expects `find_closest`, but the item only presents `restaurant_search.find_closest`

BFCL: deliberately skipped categories render as 0.00% in score CSVs and dilute Overall Acc

EvalScope integration: one-command evaluation support for BFCL-v3 and BFCL-v4

[BFCL] SerpApi is so expensive！is there any cheaper search api to alternative? And how many calls are needed to complete the web searches for these 200 pieces of web search data？

[BFCL] Question regarding Custom Handler implementation for Qwen2.5-Instruct fine-tuned on Rlla-4k (BFCL-v4)

[BFCL] OpenAICompletionsHandler: stale keep-alive connections cause spurious 400 errors

[BFCL] Function-calling parser returns empty response when tool_calls=[]

[BFCL] The most unreadable codes I have ever seen