Benchmark

MMLongBench-128K

MMLongBench-128K evaluates multimodal long-context understanding at a 128K token context length, testing how well vision-language models reason over very…

Modality
multimodal
Categories
long_context, multimodal, reasoning, vision
Openness
unknown
Source
llm_stats
Reported scores
2

Reported scores

llm_stats

ModelOrganizationReported valueReportedEvidence
Seed 2.1 ProByteDance0.7832026-06-24evidence
Seed 2.1 TurboByteDance0.7692026-06-24evidence

Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.