Benchmark Almanac

EchoChain

Grok Voice Agent 47.5% tops its leaderboard gpt-realtime 44% leads the models we track
Not in model cards

Voice agents reason through spoken exchanges while a speaker interrupts or changes instructions. The score measures whether the agent responds correctly.

Labelbox publishes the results on its leaderboard.

Made by
Labelbox
Released
March 2026
Kind
Audio understanding and voice
Level
Everyday
Scored
Graded by people
Answers
Open-ended
Tasks
Kept private
Measures
Capability
In and out
Audio → Audio
Interaction
Multi-turn
Refresh
One fixed set
Run by
A host
In views
Audio and speech
Last model added
August 2025
Scores refreshed
November 20th, 2026
4
Entries on its own leaderboard, 1 model we track

Grok Voice Agent tops the leaderboard with 47.5% gpt-realtime leads with 44%

Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. The best model we track is gpt-realtime, at 44%. This view shows only models we track, each at its best.

  1. 1 Grok Voice Agent 47.5%
  2. 2 gpt-realtime 44%
  3. 3 Amazon Nova Sonic 2 26%
  4. 4 Gemini Live-2.5-flash-native-audio 16.5%

Source: Official EchoChain leaderboard

Source: Official EchoChain leaderboard

#EntryScoreSettingDateSource
1 Grok Voice Agent 47.5% Official leaderboard
2 gpt-realtime 44% Aug 2025 Official leaderboard
3 Amazon Nova Sonic 2 26% Official leaderboard
4 Gemini Live-2.5-flash-native-audio 16.5% Official leaderboard
#ModelScoreSettingDateSource
1 gpt-realtime 44% Aug 2025 Official leaderboard

Scores over time

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

On the benchmark’s own leaderboard
0% 20% 40% 60% 80% 100% Near the ceiling (85%) gpt-realtime 0% 20% 40% 60% 80% 100% Near the ceiling (85%) gpt-realtime

Source: Official EchoChain leaderboard

No lab model card reports it yet

We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.

More in Audio and video

All 695 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%

Data audit

8 of 9 checks pass, 1 warning. Look first at the Newest score check. The newest came 15 months ago, in August 2025, for gpt-realtime. Every benchmark

Catalog record 2 pass
  • Pass Task access The tasks are private.
  • Pass Confidence Checked against a primary source.
Scores 1 warning 2 pass 2 notes
  • Pass Independent runs Scores from the official leaderboard (4 entries).
  • Note Models scored Only 1 model we track, plus 3 other entries on its leaderboard.
  • Warning Newest score The newest came 15 months ago, in August 2025, for gpt-realtime.
  • Note Frontier models None of its models are on the capabilities index.
  • Pass Headroom The best is 44%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on labelbox.com: 1 row for models we track and 3 other entries at the last read.
  • Pass Last read November 20th, 2026.
  • Pass Read worked The last read worked.
Consistency 1 pass 1 note
  • Note Lab claims No model has both a lab number and an independent run.
  • Pass Known issues No published audit found problems.

How we check