Audio2Tool (Text Oracle) - Conversation: leaderboard

Tool calling from the ground-truth text of Audio2Tool (2026) spoken requests, the oracle setting that removes speech recognition errors, on the conversation tier (multi-turn dialogues that require tracking intent and state). Exact match of the tool calls and all arguments, in percent; higher is better.

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 4,560 Tier 7 conversation queries (multi-turn dialogues of 4 to 8 turns) 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. Updated 7 Oct 2026.

Top models

#ModelScoreOverall rank
1Gemma 3 12B29.9#2091
2Qwen 3 8B28.7#1890
3Qwen 3 4B24.3#2379
4Qwen 3 1.7B20.2#5913

No result here: #2 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=audio2tool-text-oracle-conversation · How It Works · Data refreshed daily, snapshot 2026-11-22.