Audio2Tool (Text Oracle) - Direct Commands: leaderboard
Metric: Exact match (%): share of queries whose predicted tool or ordered tool sequence and all arguments exactly match the reference after deterministic normalization, on the 1,080 Tier 1 direct commands (2 to 6 words, a single tool with no arguments) of Audio2Tool, with the ground-truth text of the query given to a text LLM (the oracle setting that removes ASR errors), zero-shot; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 4 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3 8B | 85.6 |
| 2 | Gemma 3 12B | 84.1 |
| 3 | Qwen 3 4B | 80.2 |
| 4 | Qwen 3 1.7B | 74.6 |
Interactive version: theaggregate.ai/benchmark?slug=audio2tool-text-oracle-direct-commands · How It Works · Data refreshed daily, snapshot 2026-10-07.