MMGist: A Multimodal Benchmark with 7,262 Samples

MMGist is a curated multimodal evaluation benchmark built from 18 widely used vision-language benchmarks. It contains 7,262 samples spanning seven capability dimensions and is designed to make LVLM evaluation more efficient, visually grounded, discriminative, and reliable. The dataset was authored by Winston-Yuan and last updated on June 29, 2026.

Use Cases

• Benchmarking model performance based on seven capability dimensions mentioned in the description
• Evaluating visual grounding in multimodal models based on embedded image bytes
• Assessing model discriminative ability using a curated collection of 18 source benchmarks

Strengths

• Contains 7,262 samples, providing a substantial evaluation corpus
• Aggregates data from 18 widely used vision-language benchmarks
• Spans seven distinct capability dimensions for comprehensive assessment

Limitations

• Column-level documentation is absent; field semantics must be inferred after download
• Row count is unknown, which may limit suitability assessment
• Last updated 2026-06-29 08:05:28; freshness should be verified

Provenance

Source

huggingface

Collection Method

Curated from 18 widely used vision-language benchmarks

Freshness

Last updated 2026-06-29 08:05:28