Cekura Production Voice Agents
Bland 92.8 tops its leaderboard
Not in model cards Published composite score for production voice agents.
Separate task board. No combined Cekura score exists. Costs use their explicitly named units.
- Made by
- Cekura
- Released
- July 2026
- Kind
- Audio understanding and voice
- Level
- Everyday
- Scored
- Graded by a model
- Answers
- Agent task
- Tasks
- Public, plus a private test set
9
Entries on its own leaderboard, 0 models we track
Bland tops the leaderboard with 92.8
Best score per entry from the benchmark's own leaderboard, read on November 11th, 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.
- 1 Bland 92.8
- 2 Retell 92.2
- 3 Cresta 90.1
- 4 ElevenLabs 90.0
- 5 Decagon 87.4
- 6 Sierra 85.5
- 7 PolyAI 82.6
- 8 Vapi 78.3
- 9 Cognigy 73.7
Source: Official Cekura Production Voice Agents leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Bland | 92.8 | Official leaderboard | ||
| 2 | Retell | 92.2 | Official leaderboard | ||
| 3 | Cresta | 90.1 | Official leaderboard | ||
| 4 | ElevenLabs | 90.0 | Official leaderboard | ||
| 5 | Decagon | 87.4 | Official leaderboard | ||
| 6 | Sierra | 85.5 | Official leaderboard | ||
| 7 | PolyAI | 82.6 | Official leaderboard | ||
| 8 | Vapi | 78.3 | Official leaderboard | ||
| 9 | Cognigy | 73.7 | Official leaderboard |
No lab model card reports it yet
We read the headline results of 522 launch posts from 52 labs, and none of them list this benchmark.
More 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%