PARSA-Bench - Speech Translation (English to Persian): leaderboard
Metric: COMET (0-1 times 100) of Persian translations of 499 spoken English CoVoST2 utterances; zero-shot audio input, temperature 0, items with no extractable answer (including refusals) excluded; proprietary models on 100 items; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 8 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Flash | 84 | #237 |
| 2 | Qwen2.5-Omni-7B | 72 | #601 |
| 3 | Gemma 3n E4B | 71 | #856 |
| 4 | Gemma 3n E2B | 64 | #1137 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=parsa-bench-speech-translation-english-to-persian · How It Works · Data refreshed daily, snapshot 2026-10-11.