VoiceGiraffe (Cascaded Captions) - Multi-Hop Reasoning: leaderboard

VoiceGiraffe (2026) tests hour-scale audio understanding with 1,500 four-option questions on long English and Chinese recordings. Under the cascaded-caption protocol the model captions the audio in 30-second windows and then answers from its own concatenated captions; this board is accuracy in percent on the 500 multi-hop questions that link two to four distant segments, higher is better.

Metric: Accuracy (%) on the 500 multi-hop questions (causal alignment and event tracking across two to four distant segments) of VoiceGiraffe on 123 English and Chinese recordings of 30 minutes to 2 hours; cascaded caption aggregation: the model captions the recording in 30-second sliding windows (speech, speaker traits, sound events, music) and then answers from the concatenated captions and the question itself, without an external reasoning model; answers are matched by regular expression; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 12 models tracked. Updated 7 Oct 2026.

Top models

#ModelSettingScoreOverall rank
1Gemini 3.1 Pro (Preview)77.4#99
2Gemini 2.5 Pro72.2#276
3Qwen 3.5 Omni Plus66.6#254
4Qwen3.5 Omni Flash56.8#602
5Audio Flamingo 352.4
6Qwen 3 Omni 30B A3B (Thinking)49.6
7Qwen3 Omni 30B A3B Instruct46.4#930
8MOSS-Audio-8BThinking46.4#2150
9Qwen2.5-Omni-7B37#1884
10MiMo-Audio-7B32
11MOSS-Audio-8B-Instruct30.6#2017
12Phi-4 Multimodal Instruct26.8#4154

No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.

Interactive version: theaggregate.ai/benchmark?slug=voicegiraffe-cascaded-captions-multi-hop-reasoning · How It Works · Data refreshed daily, snapshot 2026-11-21.