MSI-Bench - Mandarin Scope Tracking: leaderboard

Metric: All-pass rate (%; the 96 scope-tracking cases, where group-wide and individual constraints from different speakers must be attached to their holders, Mandarin split; a case passes when all its atomic rubrics pass, judged by DeepSeek V4 Pro on the dialogue transcript, with a deterministic tool-call validator as one more rubric for cases that need a tool call; one prediction per model and case from the audio of a multi-party, multi-turn scene ending in an assistant-directed handoff; open-weight models served with JSON-schema constrained decoding). Source: arxiv.org. Saturation forecast: Around December 2026. 15 models tracked.

Top models

#ModelScore
1Gemini 3.5 Flash61.5
2Gemini 3.1 Pro (Preview)59.4
3GPT Audio35.4
4GPT Audio Mini15.6
5Qwen2.5-Omni-7B5.2
6Phi-4 Multimodal Instruct0
7Gemma 4 12B (Reasoning)0
8Gemma 4 12B (Non-reasoning)0

Interactive version: theaggregate.ai/benchmark?slug=msi-bench-mandarin-scope-tracking · How It Works · Data refreshed daily, snapshot 2026-09-26.