MultiChallenge Audio (OpenAI)
Speech-to-speech models answer an audio-friendly subset of MultiChallenge multi-turn questions that OpenAI converted from text to speech. Scored on instruction following accuracy.
OpenAI built it for the gpt-realtime launch on August 28th, 2025. It differs from Scale's later Audio MultiChallenge (audio-mc), which uses native audio conversations.
- Made by
- OpenAI
- Released
- August 2025
- Kind
- Audio understanding and voice
- Level
- Everyday
- Scored
- Graded by a model
- Answers
- Open-ended
- Tasks
- Kept private
- Last in a launch post
- August 2025, dropped before it saturated
- Last model added
- August 2025
gpt-realtime leads with 30.5%
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 gpt-realtime 30.5%
Source: Labs’ model cards
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | gpt-realtime | 30.5% | Aug 2025 | 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.
Source: Labs’ model cards
No launch post has listed it since August 2025
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.
| Date | Launch post | Score | As the post writes it |
|---|---|---|---|
| Aug 28, 2025 | gpt-realtime | 30.5 | MultiChallenge (Audio), Instruction Following |
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%