Benchmark Almanac

Speech-to-Speech Index

In use

Artificial Analysis's combined score for speech-to-speech models.

xAI quotes the index in its Grok Voice 3 launch post.

Released
October 2026
Kind
Speech recognition and translation
Level
Research frontier
Scored
Graded by a model
Answers
Open-ended
Last in a launch post
October 2026
Last model added
October 2026
2
Models scored in lab cards
2
Launch posts list it, from 1 lab

Grok Voice 3.0 leads with 86.9

Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.

  1. 1 Grok Voice 3.0 86.9
  2. 2 Grok Voice 2.0 82.9

Source: Labs’ model cards

#ModelScoreSettingDateSource
1 Grok Voice 3.0 86.9 Oct 2026 Lab model card
2 Grok Voice 2.0 82.9 Jul 2026 Lab model card

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

Reported by the lab in its model card
82 83 84 85 86 87 82 83 84 85 86 87

Source: Labs’ model cards

One lab put it in a launch post in the last six months

Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.

xAI
DateLaunch postScoreAs the post writes it
Oct 14, 2026 Grok Voice 3.0 86.9 Speech-to-Speech Index, 86.9, per Artificial Analysis
Jul 29, 2026 Grok Voice 2.0 82.9 Overall AA Speech-to-Speech Quality Index, Grok Voice 2.0, per Artificial Analysis

More in Audio and video

All 233 in Audio and video
  • Video-MMMU In use 300 expert-level lecture videos with questions testing perception, comprehension and adaptation of knowledge. Accuracy. Qwen 3.8 Max 88.7%
  • LVBench In use Hours-long video understanding with multiple-choice questions on reasoning, grounding and summarization. Gemini 4 Argon 91.7%
  • MMVU In use 3,000 expert-annotated questions on videos across 27 disciplines. Multiple-choice and open-ended accuracy. Qwen 3.8 Max 82.4%
  • MLVU In use Multi-task long video understanding (minutes to hours) with multiple-choice and generation tasks. Accuracy. Qwen 3.8 Max 90.8%
  • FLEURS In use Models transcribe read speech in 102 languages built from FLoRes-101 sentences. Model cards usually report word error rate, so lower scores are better. Phi-4-multimodal 4.00%
  • VoiceBench In use Spoken instructions with speaker, environment and content variation. Voice assistant responses scored by GPT judge or rules. Qwen3.5-Omni-Plus 93.1%