Metacognitive Control - BFCL Non-live: leaderboard
Metacognitive Control compares decoding and tool-use strategies for LLaDA model variants on function calling and multi-hop questions. Accuracy (%).
Metric: Accuracy (%). Source: arxiv.org. Saturation forecast: Rough model projection: around 2026. 6 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | LLaDA2.0-mini | 79.42 | |
| 2 | Metacognitive-controller LLaDA-8B | 65.47 | |
| 3 | Metacognitive-paper LLaDA-8B SFT | 63.6 | |
| 4 | Metacognitive-paper LLaDA-8B SFT Fast-dLLM | 52.66 | |
| 5 | LLaDA-8B-Tools | 37.27 | |
| 6 | DLLM-Searcher | 16.09 |
Interactive version: theaggregate.ai/benchmark?slug=metacognitive-control-bfcl-non-live · How It Works · Data refreshed daily, snapshot 2026-10-29.