Audio2Tool (Text Oracle) - Needle-in-a-Haystack: leaderboard

Tool calling from the ground-truth text of Audio2Tool (2026) spoken requests, the oracle setting that removes speech recognition errors, on the needle-in-a-haystack tier (tool requests buried in long irrelevant speech). 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 5 needle-in-a-haystack queries (tool calls inside long irrelevant context) 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 12B45#2059
2Qwen 3 8B44.9#1873
3Qwen 3 4B39.8#2348
4Qwen 3 1.7B35.6#5860

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=audio2tool-text-oracle-needle-in-a-haystack · How It Works · Data refreshed daily, snapshot 2026-11-21.