MTVA-Bench - Telugu: leaderboard
MTVA-Bench evaluates the language-model component of cascaded voice agents on 490 authored scenarios for 49 agents in seven languages. Each scenario uses one rollout; caller-invalid episodes are excluded. Language subsets contain different agents and tasks, rather than matched translations. This series reports MTVA-Bench - Telugu from 2609.20152v1, S7.T6: Overall Score (0-100). Higher is better.
Metric: Overall Score (0-100). Source: arxiv.org. Saturation forecast: Around February 2027. 7 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.6 Sol | 75.5 | #29 |
| 2 | Gemini 3.6 Flash | 62.3 | #74 |
| 3 | GPT-5.6 Luna | 60.5 | #118 |
| 4 | GPT-5.2 | 50.9 | #174 |
| 5 | Qwen 3.8 27B | 48.8 | #206 |
No result here: #4 Claude Opus 5.5, #5 GPT-6 Astra, #9 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=mtva-bench-telugu · How It Works · Data refreshed daily, snapshot 2026-11-08.