EVA-Bench - Accuracy: leaderboard
Metric: EVA-A pass@1 (%; share of trials in which task completion is exact, judged faithfulness is at least 0.5 and speech fidelity at least 0.95; 213 scenarios in three enterprise domains, five clean-audio trials each, averaged equally over the airline, healthcare HR and IT service management domains). Source: arxiv.org. Saturation forecast: Rough model projection: around 2026. 4 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | gpt-realtime-1.5 | 46.7 |
| 2 | Gemini 3.1 Flash Live | 29.2 |
| 3 | Ultravox-Realtime | 27 |
| 4 | GPT-Realtime-mini | 16.3 |
Interactive version: theaggregate.ai/benchmark?slug=eva-bench-accuracy · How It Works · Data refreshed daily, snapshot 2026-09-26.