Specification for a reproducible, provenance-bound multi-lane LLM benchmark suite.
-
Updated
Aug 11, 2026 - Python
#
bfcl
Here are 14 public repositories matching this topic...
Pre-generation tool-call gating via linear probes on LLM hidden states. F1 ≈ 0.91–0.94 on BFCL v4, 14–22× faster than full generation. Cross-architecture transfer across Llama / Qwen / Phi / Mistral (3B–7B) with ≥96% retention.
reproducible-research ai-safety hidden-states interpretability probing tool-use llm mechanistic-interpretability function-calling activation-patching representation-engineering bfcl linear-probe
-
Updated
May 8, 2026 - Jupyter Notebook
Canonical IR, schema validation, and deterministic delivery for function calls.
-
Updated
Aug 9, 2026 - Python
What 200 steps of fully simulated multi-turn tool-use RL do to a 4B policy: every 10th checkpoint scored on BFCL v4, with the pipeline that produced the measurement.
-
Updated
Aug 12, 2026 - Python
A bf16 LoRA fine-tune of Qwen 3.5 4B for function calling on xLAM. v1.0 ships below the BFCL gate with full per-category failure analysis.
-
Updated
May 16, 2026 - Python
Paired metamorphic evaluation of tool-calling robustness under realistic user phrasing, built on BFCL.
-
Updated
Aug 9, 2026 - Python
Open LLM leaderboard featuring Xiaomi MiMo v2.5 & MiMo 100T head-to-head with GPT-5, Claude, Gemini, DeepSeek, Llama 4. ARC-AGI · SWE-Bench · MMLU-Pro · GPQA · HumanEval · BFCL.
react nextjs gemini llama claude tailwindcss mimo humaneval gpt-5 deepseek llm-leaderboard tool-calling arc-agi bfcl gpqa swe-bench llm-benchmark xiaomi-mimo mimo-100t mmlu-pro
-
Updated
May 18, 2026 - TypeScript
Independent audit of a fine-tuned LLM tool-calling PoC — BFCL regression decomposition, inference stack risk assessment, and production recommendation for a FinTech client. Qwen-2.5, LoRA, SGLang, H100.
machine-learning inference fintech lora model-evaluation fine-tuning mlops huggingface llm vllm function-calling qwen sglang bfcl toolace
-
Updated
Apr 27, 2026 - Python
QLoRA fine-tune of Qwen2.5-1.5B for tool calling on one 8 GiB GPU: +8.5% on BFCL call categories, -55 points on the ability to decline. Refusal data recovers ~49 of them, reproduced across 3 seeds.
-
Updated
Aug 14, 2026 - Python
OpenEuroLLM snapshot of the Berkeley Function Calling Leaderboard evaluation harness and OLMo evaluation orchestration.
-
Updated
Aug 3, 2026 - Python
A compact, model-first notation for LLM tool definitions. Re-encodes JSON Schema with a median ~30% input-token reduction and behavior-preserving fallback. Includes the specification, a reference converter, a deployment protocol, and the full evaluation.
json-schema reproducible-research evaluation notation large-language-models llm prompt-engineering llm-tools function-calling llm-agents tool-calling bfcl token-optimization
-
Updated
Aug 2, 2026 - Python
Tool-call reliability fine-tuning lab with open-weight model training, benchmark evaluation, and serving notes.
-
Updated
Aug 12, 2026 - Python
Improve this page
Add a description, image, and links to the bfcl topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the bfcl topic, visit your repo's landing page and select "manage topics."