Official provider results
Eleven Realtime provider evaluation
ElevenLabs reports separate speech-reasoning, conversation, human-preference, task-success, and response-latency measurements for Eleven Realtime v1 Mini and Max.
Source snapshots refreshed
Five measurement lanesVOICE / S2S
Reasoning, task completion, conversation dynamics, experience, and latency stay separate.
Benchmark profile
- Scope
- Two hosted voice-agent systems; separate evaluations
- Primary metric
- Separate native percentages, Elo, and mean time to first audio in milliseconds
- Owner
- ElevenLabs
- Available evidence
- Provider-published selected figures; no shared overall score
What it measures
Spoken reasoning
Does the system understand and answer spoken requests?
Task completion
Can it follow policy, use tools, and finish a workflow?
Conversation dynamics
Can it handle turns, interruptions, ambiguity, and state?
Voice experience
Is the exchange natural, robust, and responsive?
Latency
How long do responses, tool calls, and full tasks take?
Available results
Selected published results
Figures published by ElevenLabs. Missing cells mean the product page did not publish that measurement for the model.
| Model | Mean first audio (ms) | Full-Duplex-Bench (%) | Speech Agent Arena Elo | Big Bench Audio (%) | Task success (%) |
|---|---|---|---|---|---|
| Eleven Realtime v1 Mini | 620 | 95.8 | 988 | Not reported | Not reported |
| Eleven Realtime v1 Max | 570 | Not reported | Not reported | 98.8 | 87.1 |
Interpretation limit
These are selected figures published by ElevenLabs and attributed to an independent evaluator, rather than a complete independently retrieved leaderboard. Big Bench Audio, Full-Duplex-Bench, Speech Agent Arena Elo, task success, and latency have different units and protocols. The page gives no sample counts, uncertainty, evaluation dates, task-success rubric, or benchmark version for Full-Duplex-Bench. Time to first audio is the average measured on Big Bench Audio. Do not merge these figures with similarly named existing benchmark versions or rank Mini against Max on metrics published for only one of them. The third-party figures are not licensed here for Data API redistribution.