Benchmark
MMLongBench-128K
What is MMLongBench-128K?
MMLongBench-128K evaluates multimodal long-context understanding at a 128K token context length, testing how well vision-language models reason over very long…
- Modality
- multimodal
- Evaluates
- long context, multimodal, reasoning, vision
- Openness
- unknown
- Importer
- LLM Stats
- Reported scores
- 2
Source provenance
MMLongBench-128K results and reported scores
LLM Stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Seed 2.1 Pro | ByteDance | 0.783 | 2026-06-24 | evidence |
| Seed 2.1 Turbo | ByteDance | 0.769 | 2026-06-24 | evidence |
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.