VoxParity
Voice agents choose tool calls after listening to speech. Paired recordings keep the words fixed while changing an audible cue that affects the correct action.
The public development set contains 40 of the 183 scenarios. The leaderboard also includes held-out scenarios.
- Made by
- Bhavik Mangla
- Released
- September 2026
- Kind
- Audio understanding and voice
- Level
- Everyday
- Scored
- Checked automatically
- Answers
- Agent task
- Tasks
- Public, plus a private test set
- Measures
- Capability
- Language
- English
- Interaction
- Single turn
- Environment
- APIs and tools
- Refresh
- One fixed set
- Run by
- A host
- In views
- Audio and speech, Content safety
- Strongest model tested
-
Gemini 3.8 Flash #24 on the capability index
- Last model added
- September 2026
- Scores refreshed
- November 20th, 2026
Qwen3.8-Omni (file) tops the leaderboard with 0.25 Gemini 3.7 Flash leads with 0.23 among models released by September 2026
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 Gemini 3.7 Flash, at 0.23. This view shows only models we track, each at its best.
The newest model with a score here came out in September 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- Claude Opus 5.5
- and 16 more
- 0.25 Qwen3.8-Omni (file)
- 0.23
Gemini 3.7 Flash
- 0.20 MiMo-V2.6 Pro
- 0.20 Inkling (BaseTen upstream)
- 0.18 StepAudio 3
- 0.18
Gemini 3.8 Flash
- 0.17 MiMo-V2.6 Flash
- 0.15 Gemini 2.5 native-audio Live
- 0.12 MiMo-V2.5
- 0.11
Voxtral Small
- 0.10
Qwen2.5-Omni-7B
- 0.09
Gemini 3.1 Flash Live
- 0.07
Gemini 3.8 Live
- 0.07
Muse Spark 1.2
- 0.05 Qwen3-Omni-30B (local)
- 0.05 GPT-Realtime-2.1
- 0.04 GPT-Realtime-2.1 Mini
- 0.04 Gemma-4-E4B (local)
- 0.00
Phi-4-multimodal
- 0.00 Gemma-4-12B (local)
- -0.00 Qwen-Audio-3.1 RT
- -0.00 Grok Voice
- -0.10
Nemotron 3 Nano Omni 30B-A3B
- 1 Qwen3.8-Omni (file) file 0.25
- 2
Gemini 3.7 Flash file 0.23
- 3 MiMo-V2.6 Pro file 0.20
- 4 Inkling (BaseTen upstream) file 0.20
- 5 StepAudio 3 file 0.18
- 6
Gemini 3.8 Flash file 0.18
- 7 MiMo-V2.6 Flash file 0.17
- 8 Gemini 2.5 native-audio Live realtime 0.15
- 9 MiMo-V2.5 file 0.12
- 10
Voxtral Small file 0.11
- 11
Qwen2.5-Omni-7B local 0.10
- 12
Gemini 3.1 Flash Live realtime 0.09
- 13
Gemini 3.8 Live realtime 0.07
- 14
Muse Spark 1.2 file 0.07
- 15 Qwen3-Omni-30B (local) local 0.05
- 16 GPT-Realtime-2.1 realtime 0.05
- 17 GPT-Realtime-2.1 Mini realtime 0.04
- 18 Gemma-4-E4B (local) local 0.04
- 19
Phi-4-multimodal local 0.00
- 20 Gemma-4-12B (local) local 0.00
- 21 Qwen-Audio-3.1 RT realtime -0.00
- 22 Grok Voice realtime -0.00
- 23
Nemotron 3 Nano Omni 30B-A3B file -0.10
Source: Official VoxParity leaderboard
- 0.23
Gemini 3.7 Flash
- 0.20 MiMo-V2.6 Pro
- 0.18
Gemini 3.8 Flash
- 0.17 MiMo-V2.6 Flash
- 0.12 MiMo-V2.5
- 0.11
Voxtral Small
- 0.10
Qwen2.5-Omni-7B
- 0.09
Gemini 3.1 Flash Live
- 0.07
Gemini 3.8 Live
- 0.07
Muse Spark 1.2
- 0.05 GPT-Realtime-2.1
- 0.04 GPT-Realtime-2.1 Mini
- 0.00
Phi-4-multimodal
- -0.10
Nemotron 3 Nano Omni 30B-A3B
- 1
Gemini 3.7 Flash file 0.23
- 2 MiMo-V2.6 Pro file 0.20
- 3
Gemini 3.8 Flash file 0.18
- 4 MiMo-V2.6 Flash file 0.17
- 5 MiMo-V2.5 file 0.12
- 6
Voxtral Small file 0.11
- 7
Qwen2.5-Omni-7B local 0.10
- 8
Gemini 3.1 Flash Live realtime 0.09
- 9
Gemini 3.8 Live realtime 0.07
- 10
Muse Spark 1.2 file 0.07
- 11 GPT-Realtime-2.1 realtime 0.05
- 12 GPT-Realtime-2.1 Mini realtime 0.04
- 13
Phi-4-multimodal local 0.00
- 14
Nemotron 3 Nano Omni 30B-A3B file -0.10
Source: Official VoxParity leaderboard
| # | Entry | Score ± | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Qwen3.8-Omni (file) | 0.25 ±0.1 | file | Official leaderboard | |
| 2 | | 0.23 0.2 to 0.3 | file | Aug 2026 | Official leaderboard |
| 3 | MiMo-V2.6 Pro | 0.20 0.1 to 0.3 | file | Sep 2026 | Official leaderboard |
| 4 | Inkling (BaseTen upstream) | 0.20 ±0.1 | file | Official leaderboard | |
| 5 | StepAudio 3 | 0.18 0.1 to 0.2 | file | Official leaderboard | |
| 6 | | 0.18 0.1 to 0.3 | file | Sep 2026 | Official leaderboard |
| 7 | MiMo-V2.6 Flash | 0.17 0.1 to 0.3 | file | Sep 2026 | Official leaderboard |
| 8 | Gemini 2.5 native-audio Live | 0.15 ±0.1 | realtime | Official leaderboard | |
| 9 | MiMo-V2.5 | 0.12 ±0.1 | file | Apr 2026 | Official leaderboard |
| 10 | | 0.11 ±0.1 | file | Jul 2025 | Official leaderboard |
| 11 | | 0.10 ±0.1 | local | Mar 2025 | Official leaderboard |
| 12 | | 0.09 ±0.1 | realtime | Mar 2026 | Official leaderboard |
| 13 | | 0.07 ±0.1 | realtime | Sep 2026 | Official leaderboard |
| 14 | | 0.07 ±0.1 | file | Aug 2026 | Official leaderboard |
| 15 | Qwen3-Omni-30B (local) | 0.05 ±0.1 | local | Official leaderboard | |
| 16 | GPT-Realtime-2.1 | 0.05 0 to 0.1 | realtime | Jul 2026 | Official leaderboard |
| 17 | GPT-Realtime-2.1 Mini | 0.04 0 to 0.1 | realtime | Jul 2026 | Official leaderboard |
| 18 | Gemma-4-E4B (local) | 0.04 ±0 | local | Official leaderboard | |
| 19 | | 0.00 ±0.1 | local | Feb 2025 | Official leaderboard |
| 20 | Gemma-4-12B (local) | 0.00 0 to 0 | local | Official leaderboard | |
| 21 | Qwen-Audio-3.1 RT | -0.00 ±0.1 | realtime | Official leaderboard | |
| 22 | Grok Voice | -0.00 -0.1 to 0 | realtime | Official leaderboard | |
| 23 | | -0.10 ±0.1 | file | Apr 2026 | Official leaderboard |
| # | Model | Score ± | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 0.23 0.2 to 0.3 | file | Aug 2026 | Official leaderboard |
| 2 | MiMo-V2.6 Pro | 0.20 0.1 to 0.3 | file | Sep 2026 | Official leaderboard |
| 3 | | 0.18 0.1 to 0.3 | file | Sep 2026 | Official leaderboard |
| 4 | MiMo-V2.6 Flash | 0.17 0.1 to 0.3 | file | Sep 2026 | Official leaderboard |
| 5 | MiMo-V2.5 | 0.12 ±0.1 | file | Apr 2026 | Official leaderboard |
| 6 | | 0.11 ±0.1 | file | Jul 2025 | Official leaderboard |
| 7 | | 0.10 ±0.1 | local | Mar 2025 | Official leaderboard |
| 8 | | 0.09 ±0.1 | realtime | Mar 2026 | Official leaderboard |
| 9 | | 0.07 ±0.1 | realtime | Sep 2026 | Official leaderboard |
| 10 | | 0.07 ±0.1 | file | Aug 2026 | Official leaderboard |
| 11 | GPT-Realtime-2.1 | 0.05 0 to 0.1 | realtime | Jul 2026 | Official leaderboard |
| 12 | GPT-Realtime-2.1 Mini | 0.04 0 to 0.1 | realtime | Jul 2026 | Official leaderboard |
| 13 | | 0.00 ±0.1 | local | Feb 2025 | Official leaderboard |
| 14 | | -0.10 ±0.1 | file | Apr 2026 | Official leaderboard |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official VoxParity leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official VoxParity 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
- 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
All 9 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access Public tasks, plus a private test set.
- Pass Confidence Checked against a primary source.
Scores 3 pass 2 notes
- Pass Independent runs Scores from the official leaderboard (23 entries).
- Pass Models scored 14 models we track, plus 9 other entries on its leaderboard.
- Pass Newest score The newest is from September 2026, for MiMo-V2.6 Flash.
- Note Frontier models None of the top 10 has a score. The strongest tested is Gemini 3.8 Flash (#24).
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on huggingface.co: 14 rows for models we track and 9 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.