gpt-realtime
gpt-realtime.
7
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
OpenAI Aug 2025
gpt-realtime
Closed weights Flagship
No Epoch Capabilities Index score yet
- Audio MC 23.4% #13 /18
- τ-Voice 30.4% #7 /7
- Big Bench Audio 82.8% #5 /7
Where it ranks
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| ComplexFuncBench Audio (OpenAI) | 66.5% | #1 of 1 | Lab model card |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| vCX Benchmark | 86% | #22 of 42 | Official leaderboard | |
| Big Bench Audio | 82.8% | #5 of 7 | Lab model card | |
| Audio MC | 23.4% | #13 of 18 | Official leaderboard | |
| EVA-Bench | 0.41 | #7 of 8 | Official leaderboard | |
| τ-Voice | 30.4% | #7 of 7 | Official leaderboard | |
| MultiChallenge Audio (OpenAI) | 30.5% | #1 of 1 | Lab model card |
Its launch post
The benchmarks the lab chose to headline, with the scores it gave.