R2-Omni - LongVALE SODA-C (Uncompressed): leaderboard

R2-Omni v1 Table1, original uncompressed Omni-LLMs with native audio-visual pipelines and greedy decoding. LongVALE SODA-C measures long-form audio-visual event description; event-error rate is lower-is-better. Compression methods and normalized relative-quality scores are kept outside the original-model baseline. No unsupported finite upper bound is assigned to EER or SODA metrics. Reported metric: LongVALE SODA-C.

Metric: LongVALE SODA-C. Source: arxiv.org. Saturation forecast: Rough model projection: around 2026. 3 models tracked.

Top models

#ModelScoreOverall rank
1Qwen2.5-Omni-7B1.63#633

No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.

Interactive version: theaggregate.ai/benchmark?slug=r2-omni-longvale-soda-c-uncompressed · How It Works · Data refreshed daily, snapshot 2026-11-05.