AudioMultiChallenge

AudioMultiChallenge is a knowledge benchmark in the BenchGecko catalog. 2 AI models have been tested on it. Scores range from 40.0 to 46.9 out of 100.

Gemini 2.5 Pro from Google DeepMind leads AudioMultiChallenge with a score of 46.9. The median score across 2 tested models is 43.5.

No · the top score is 46.9 out of 100 (47%). There is still meaningful room for improvement on AudioMultiChallenge.

AudioMultiChallenge is a knowledge benchmark with limited overlap to the rest of the catalog · it measures capabilities that are not well-covered by other benchmarks we track.

BenchGecko pulls updates daily. New model scores on AudioMultiChallenge appear as soon as they are published by Epoch AI or the model provider.