Afrispeech Semantics - Entailment (AfriSpeech-Medical): leaderboard
Three-way audio entailment on African-accented clinical conversations (Afrispeech Semantics, Okocha and Grant, 2026): the model decides whether the spoken premise entails, contradicts or leaves undetermined each human-verified text hypothesis. Macro-F1 in percent for audio language models prompted zero-shot; higher is better.
Metric: Macro-F1 (%; three-way entailment, neutral or contradiction judgments of text hypotheses against a spoken premise, computed over all premise-hypothesis pairs of the AfriSpeech-Medical clinical-dialogue set; zero-shot generative audio language model, free-form answers mapped to labels by a lightweight language model). Source: arxiv.org. Saturation forecast: Around February 2027. 7 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen2.5-Omni-7B | 52.74 | #1797 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=afrispeech-semantics-entailment-afrispeech-medical · How It Works · Data refreshed daily, snapshot 2026-11-12.