Skip to content
localmodel.run

Leaderboard · BFCL

Local LLM tool-use leaderboard

The Berkeley Function-Calling Leaderboard (BFCL) tests tool selection and arguments. Our catalog stores Overall Acc, taking the native function-calling (FC) result where available. The exact source snapshot and benchmark version need re-verification; do not compare these legacy scores with the current source board or use them to establish complete agent performance.

Benchmark verification dates are not yet recorded. The model-size refresh does not recheck scores; consult the source leaderboard for current results. Hardware fit below is estimated at Q4_K_M and does not establish the same benchmark performance.

19 models · ranked by BFCL runs on
  1. 1 59.1% KI Kimi K2 Instruct 1000B MoE
  2. 2 48.7% Qwen3 32B 32B
  3. 3 46.5% CR Command A 111B
  4. 4 42.6% Qwen3 8B 8B
  5. 5 41% Qwen3 14B 14B
  6. 6 37.3% Llama 4 Maverick 400B MoE
  7. 7 31.9% Llama 3.3 70B 70B
  8. 8 30.4% Gemma 3 12B 12B
  9. 9 29.5% Gemma 3 27B 27B
  10. 10 28.8% Phi-4 14B 14B
  11. 11 28.4% Qwen3 1.7B 1.7B
  12. 12 28.1% Llama 4 Scout 109B MoE
  13. 13 27% FN Falcon3 10B 10B
  14. 14 25.8% Llama 3.1 8B 8B
  15. 15 23.9% Qwen3 0.6B 600M
  16. 16 22% Llama 3.2 3B 3B
  17. 17 19.6% Gemma 3 4B 4B
  18. 18 10.8% Llama 3.2 1B 1B
  19. 19 7.2% Gemma 3 1B 1B

Score is BFCL (recorded overall accuracy on the berkeley function-calling leaderboard.), sourced from gorilla.cs.berkeley.edu/leaderboard. The "runs on" column is the lightest tracked device that runs the model at Q4_K_M; tap a model for the full hardware list. Coverage is partial: only models we verified against the canonical board appear.

On agentic leaderboards

Tool-call accuracy is one part of an agent's performance. Completing a task also depends on the harness, prompts, available tools and retry budget. Compare whole-task results only when those conditions match; a BFCL score alone cannot tell you whether a local model will replace a hosted coding agent.

Other boards

Local LLM coding leaderboard Percent of 225 Exercism exercises solved across six languages. Local LLM chat leaderboard Human-preference Elo from LMArena's blind head-to-head votes.

Or pick by what you need with use-case picks, or browse the full model list.

FAQ

Which tracked model has the highest recorded tool use score?

Kimi K2 Instruct leads our partial catalog at 59.1% on BFCL. This does not establish the current overall leader. It needs ~586.6 GB at Q4_K_M, more than any single tracked device, so it wants a high-memory rig. The hardware figure is an estimate, not a measured benchmark run on that device.

How is this tool use leaderboard scored?

The Berkeley Function-Calling Leaderboard (BFCL) tests tool selection and arguments. Our catalog stores Overall Acc, taking the native function-calling (FC) result where available. The exact source snapshot and benchmark version need re-verification; do not compare these legacy scores with the current source board or use them to establish complete agent performance. We only list a model after verifying its score against the canonical leaderboard for that exact model, so coverage is partial by design. Source: gorilla.cs.berkeley.edu/leaderboard.

Can I run these models locally?

Every row shows the lightest tracked device that runs the model at Q4_K_M and links to the full hardware list, so you see the ranking and your hardware fit together.

Benchmark scores come from gorilla.cs.berkeley.edu/leaderboard and describe its evaluation setup. Memory-data refresh: 2026-09-14; this is not a benchmark verification date. See methodology.